doi
stringlengths 10
10
| chunk-id
int64 0
936
| chunk
stringlengths 401
2.02k
| id
stringlengths 12
14
| title
stringlengths 8
162
| summary
stringlengths 228
1.92k
| source
stringlengths 31
31
| authors
stringlengths 7
6.97k
| categories
stringlengths 5
107
| comment
stringlengths 4
398
⌀ | journal_ref
stringlengths 8
194
⌀ | primary_category
stringlengths 5
17
| published
stringlengths 8
8
| updated
stringlengths 8
8
| references
list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2306.05685
| 53 |
[51] Wanjun Zhong, Ruixiang Cui, Yiduo Guo, Yaobo Liang, Shuai Lu, Yanlin Wang, Amin Saied, Weizhu Chen, and Nan Duan. Agieval: A human-centric benchmark for evaluating foundation models. arXiv preprint arXiv:2304.06364, 2023.
[52] Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206, 2023.
13
# A Prompt templates
We list the prompt templates for LLM judges. Please refer to our github repository 3 for full details.
# [System]
|
2306.05685#53
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 53 |
We acknowledge that the help request functionality in this course is not something that every student is eager to use. Some students will have needed help but decided not to ask for it. Prior research on a help request platform for programming noted that only one third of the students who open up a help request dialog end up writing a help request, and that even the prompts used in the help request dialog can inï¬uence whether a help request gets sent [77]. Platform functionality aside, students may seek help from many sources, such as their peers or online services [48, 50, 58, 60]ânow from public LLMs as well. Instead of seeking help, students may also resort to plagiarism [26] or simply drop out [64].
Future research should seek to detect when students need help in order to provide timely feedback [34, 44, 54]. That research might be informed by prior work, which has highlighted that data col- lected from the programming process encodes information about studentsâ struggles [1, 5, 13, 33, 42, 54, 69, 88]. Including such pro- cess data in help requests has unexplored potential that might be fulï¬lled through dedicated LLMs, for example.
|
2306.05715#53
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 53 |
Observation 4: Small LMs enhance domain capabilities at the expense of generic capabilities In our experiments, we examined two medical LLMs: DoctorGLM and Baize-Healthcare. DoctorGLM originated from ChatGLM-6B, and Baize-Healthcare was derived from Llama-7B, with both models fine-tuned using medical domain text. Although both models have lower MRR compared to other LLMs fine-tuned based on the same base models, they each demonstrate high performance in medical domain. This suggests the augmentation of LLMs with fewer parameters in domain text comprehension, whether finetuned through exclusively domain-specific data or combining domain- specific and generic data, will inevitably lead to a trade-off in the understanding of generic text. This observation aligns with the findings from previous research Fu et al. (2023); Zhao et al. (2023).
# 4.3 Results of Benchmarks
|
2306.05783#53
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 53 |
The user-side fairness in recommender systems requires similar users to be treated similarly at either individual level or group level. The user sensitive attributes should not be preset during recommendation (e.g., gender, race). To this end, UP5 [Hua et al., 2023a] proposes counterfactually fair prompting (CFP), which consists of a personalized preï¬x prompt and a prompt mixture to ensure fairness w.r.t. a set of sensitive attributes. Besides, Zhang et al. [2023a] intro- duce a benchmark named FaiRLLM, where authors comprise carefully crafted metrics and a dataset that accounts for eight sensitive attributes in recommendation scenarios where LLM is involved. Yet these studies only focus on the fairness issue in speciï¬c recommendation tasks (e.g., item generation task) with limited evaluation metrics.
The item-side fairness in recommender systems ensures that each item or item group receives a fair chance to be rec- ommended (e.g., proportional to its merits or utility) [Patro et al., 2020; Liu et al., 2019; Singh and Joachims, 2018]. How- ever, how to improve item-side fairness in LLM remains less
|
2306.05817#53
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 53 |
# 4.2.3.2 Imposing Norms and Values
Global deployment of a model can consolidate power within a single, originating culture, to determine and propagate acceptability [245] across cultures [150]. Highest performing characteristics of gener- ative systems such as language, dominant cultural values, and embedded norms can overrepresent regions outside of where a system is deployed. For example, a language model that is highest performing in the English language can be deployed in a region with a different dominant language and incentivize engaging in English. Establishing or reinforcing goodness with certain languages, accents, imagery, social norms, and other representations of peoples and cultures can contribute to this norms and values imposition.
Certain modality characteristics such as language carry within it its own logics and frames. Though English as a lingua franca is globally beneficial, the consequences of its dominance as a result of a historic process of militarised colonization should be examined. Insidious effects which generative AI systems could further embed include the erosion of global multilingualism, undermine the right to language and culture, and further marginalize the necessity for widespread multilingual education.
|
2306.05949#53
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 53 |
12
[20] Minghao Li, Feifan Song, Bowen Yu, Haiyang Yu, Zhoujun Li, Fei Huang, and Yongbin Li. Api-bank: A benchmark for tool-augmented llms. CoRR, abs/2304.08244, 2023. doi: 10.48550/arXiv.2304.08244. URL https://doi.org/10.48550/arXiv.2304.08244.
[21] Yang Li, Jiacong He, Xin Zhou, Yuan Zhang, and Jason Baldridge. Mapping natural language instructions to mobile UI action sequences. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 8198â8210. Association for Computational Linguistics, 2020. doi: 10.18653/v1/2020.acl-main.729. URL https: //doi.org/10.18653/v1/2020.acl-main.729.
|
2306.06070#53
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 53 |
However, for certain applications, one can construct powerful prototypes using only
careful prompting. For instance, the InsightGraph team (Defne Circi, Shruti Badhwar) showed that GPT-3.5-turbo, when prompted with an example JSON containing a high- level schema and information on possible entities (e.g., materials) and pairwise relation- ships (e.g., properties), can, as Figure 7 illustrates, provide a knowledge graph repre- sentation of the entities and their relationships in a text describing the properties and composition of polymer nanocomposites. A further optimized version of this tool might oï¬er a concise and visual means to quickly understand and compare material types and uses across sets of articles and could be used to launch a literature review. An ad- vanced potential application is the creation of structured, materials-speciï¬c datasets for fact-based question-answering and downstream machine-learning tasks.
b. Extracting Structured Data from Free-form Organic Synthesis Text
Unstructured text is commonly used for describing organic synthesis procedures. Due to the large corpus of literature, manual conversion from unstructured text to struc20
|
2306.06283#53
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 53 |
Colleen M Seifert, Andrea L Patalano, Kristian J Hammond, and Timothy M Converse. Experience and expertise: The role of memory in planning for opportunities. 1997.
Noah Shinn, Beck Labash, and Ashwin Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection. CoRR, abs/2303.11366, 2023. doi: 10.48550/arXiv.2303.11366. URL https://doi.org/10.48550/arXiv.2303.11366.
Thomas Suddendorf and Michael C Corballis. The evolution of foresight: What is mental time travel, and is it unique to humans? Behavioral and brain sciences, 30(3):299â313, 2007.
Richard S Sutton and Andrew G Barto. Reinforcement learning: An introduction. Robotica, 17(2): 229â235, 1999.
|
2306.07929#53
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 54 |
13
# A Prompt templates
We list the prompt templates for LLM judges. Please refer to our github repository 3 for full details.
# [System]
Please act as an impartial judge and evaluate the quality of the responses provided by two AI assistants to the user question displayed below. You should choose the assistant that follows the userâs instructions and answers the userâs question better. Your evaluation should consider factors such as the helpfulness, relevance, accuracy, depth, creativity, and level of detail of their responses. Begin your evaluation by comparing the two responses and provide a short explanation. Avoid any position biases and ensure that the order in which the responses were presented does not influence your decision. Do not allow the length of the responses to influence your evaluation. Do not favor certain names of the assistants. Be as objective as possible. After providing your explanation, output your final verdict by strictly following this format: "[[A]]" if assistant A is better, "[[B]]" if assistant B is better, and "[[C]]" for a tie.
[User Question] {question} [The Start of Assistant Aâs Answer] {answer_a} [The End of Assistant Aâs Answer] [The Start of Assistant Bâs Answer] {answer_b} [The End of Assistant Bâs Answer]
Figure 5: The default prompt for pairwise comparison.
# [System]
|
2306.05685#54
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 54 |
5.5.2 Context-Dependent Issues in Student Code. Many of the stu- dent programs had multiple issues, and some types of issues were more frequent than others. This is unsurprising and in line with prior research on logic and syntax errors [3, 10, 15, 15, 20, 32, 56, 57, 80, 86]. Like Ettles et al. [21], and again unsurprisingly, we ob- served that the distribution of issues depended on the exercise.
Many of the help requests involved input and output (with the theme present in 34% of the requests). These issues were especially common very early on in the course, when students were prac- ticing I/O. Upon further reï¬ection, some of the issues are in part
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, and Juha Sorva
explained by worked examples in the course materials: for exam- ple, in one exercise, many students had incorrect formatting appar- ently because they had copied the output format not from the exer- cise handout but from a similar-looking worked example that im- mediately preceded the exercise. Such struggles with I/O reduced later on in the course, perhaps suggesting that students learned to pay closer attention to the handouts.
|
2306.05715#54
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 54 |
# 4.3 Results of Benchmarks
Based on the observations from Tab. 2, although the objective is to comprehensively evaluate the domain capabilities of LLMs, the various benchmarks still exhibit differing results, which indicates the different emphases of each benchmark. GPT-4, ChatGPT, and Bloomz-mt consistently rank within the top 10 across all four benchmarks, Baize-7b, and Bloomz-7b1 demonstrate remarkable abilities as they rank within the top 10 across three of the benchmarks. Furthermore, Xiezhi exhibits the highest variance among all LLMs in the "Performance-Variance" of Tab. 1, while GPT-4âs MRR score of Xiezhi does not considerably surpass other benchmarks in Tab. 2. This indicates that the Xiezhi Benchmark excels at discerning the competence disparities among diverse LLMs and possesses the potential to appraise more potent LLMs.
# 5 Discussion
# Large Language Models Need More Benchmarks
|
2306.05783#54
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 54 |
explored. As a preliminary study, Hou et al. [2023b] observe that popularity bias exists when LLM serves as a ranking function, and alleviate the bias to some extents by designing prompts to guide the LLM focusing on usersâ historical inter- actions. Further studies on popularity bias and other potential item-wise fairness issues are still needed.
# 5 Conclusion and Future Prospects
This survey comprehensively summarizes the recent progress in adapting large language models to recommender systems from two perspectives: where and how to adapt LLM to RS.
⢠For the âWHEREâ question, we analyze the roles that LLM could play at different stages of the recommendation pipeline, i.e., feature engineering, feature encoder, scor- ing/ranking function, and pipeline controller.
⢠For the âHOWâ question, we analyze the training and in- ference strategies, resulting in two orthogonal classiï¬ca- tion criteria, i.e., whether to tune LLM, and whether to in- volve CRM for inference.
Detailed discussions and insightful development trajecto- ries are also provided for each taxonomy perspective. As for future prospects, apart from the three aspects we have already highlighted in Section 4 (i.e., efï¬ciency, effectiveness and ethics), we would like to further express our hopeful vision for the future development of combining large language mod- els and recommender systems:
|
2306.05817#54
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 54 |
The effects of generative AI systems on child development, including the technologically mediated socialisation of norms and values is also an area to be inquired. These are in addition to the emotional and behavioural effects of chatbots on children. This, according to UNICEF [248], included the enforcement of "bias, given that they often select a predetermined reply based on the most matching keywords or similar wording pattern".
15
What to Evaluate In addition to evaluations and limitations in 4.1.2 Cultural Values and Sensitive Content, complex, qualitative, and evolving cultural concepts such as beauty and success are viewed differently in context of an application and cultural region. Impacts of norm and value impositions are still being determined, but can manifest in a given use case [130].
Mitigation and Interventions Mitigations should be cognizant of preserving irreducible differences among cultures [73] and practicing value sensitive design [84], including by focusing on system components such as data extraction and use [62]. Methods for cultural value alignment [228] can improve and require improving methods and infrastructure for working with underrepresented groups. Novel alignment techniques [259, 25] by modality can determine preferable principles and values for generative AI systems. Prominent AI regulations such as the EU AI Act should account for copycat legislation in other countries.
# 4.2.4 Labor and Creativity
|
2306.05949#54
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 54 |
[22] Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, and Percy Liang. Reinforcement learning on web interfaces using workflow-guided exploration. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net, 2018. URL https://openreview.net/ forum?id=ryTp3f-0-.
[23] Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ramakanth Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, Edouard Grave, Yann LeCun, and Thomas Scialom. Augmented language models: a survey. CoRR, abs/2302.07842, 2023. doi: 10.48550/arXiv.2302.07842. URL https://doi.org/10.48550/ arXiv.2302.07842.
[24] OpenAI. Chatgpt plugins. https://openai.com/blog/chatgpt-plugins. 2023.
[25] OpenAI. Gpt-4 technical report, 2023.
|
2306.06070#54
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 54 |
Unstructured text is commonly used for describing organic synthesis procedures. Due to the large corpus of literature, manual conversion from unstructured text to struc20
A suspension of compound 63 (0.22 g, 0.93 mmol) and 64 (0.33 g, 0.92 mmol) in THF/triethylamine (11 mL, 10/1) was stirred at room temperature for 48 h. After this time, a clear solution was formed. The solvent was removed under reduced pressure and the residue was purified by flash chromatography (silica gel, 10:1:0.1 chloroform/methanol/concentrated ammonium hydroxide) to provide the quanidine 65 (0.3 q, 60%) as a yellow solid. 1H NMR (300 MHz, DMSO-d6) 5 1.42 (5, 9H), 1.55 (m, 4H), 2.19 (5, 6H), 2.58 (m, 4H), 3.99 (m, 2H), 6.83 (d, 2H), 7.12 (d, 2H), 7.40 (br s, 2H), 9.02 (m, 2H). "identifiers": [ "amount"
|
2306.06283#54
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 54 |
Richard S Sutton and Andrew G Barto. Reinforcement learning: An introduction. Robotica, 17(2): 229â235, 1999.
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. Interleaving re- trieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. CoRR, abs/2212.10509, 2022. doi: 10.48550/arXiv.2212.10509. URL https://doi.org/10.48550/ arXiv.2212.10509.
Hado van Hasselt. Double q-learning. In John D. Lafferty, Christopher K. I. Williams, John Shawe- Taylor, Richard S. Zemel, and Aron Culotta, editors, Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, Vancouver, British Columbia, Canada, pages 2613â2621. Curran Associates, Inc., 2010. URL https://proceedings.neurips.cc/paper/2010/hash/ 091d584fced301b442654dd8c23b3fc9-Abstract.html.
|
2306.07929#54
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 55 |
Figure 5: The default prompt for pairwise comparison.
# [System]
Please act as an impartial judge and evaluate the quality of the response provided by an AI assistant to the user question displayed below. Your evaluation should consider factors such as the helpfulness, relevance, accuracy, depth, creativity, and level of detail of the response. Begin your evaluation by providing a short explanation. Be as objective as possible. After providing your explanation, please rate the response on a scale of 1 to 10 by strictly following this format: "[[rating]]", for example: "Rating: [[5]]".
[Question] {question} [The Start of Assistantâs Answer] {answer} [The End of Assistantâs Answer]
Figure 6: The default prompt for single answer grading.
3https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge
14
[System]
|
2306.05685#55
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 55 |
In some cases, it was evident that a student had correctly in- terpreted what they were supposed to achieve overall, but had omitted a part of the solution, perhaps simply by overlooking a re- quirement or because they were testing the program with speciï¬c inputs. This was present especially in the more complex âRainfall- problem-likeâ exercises of the course, which are known to be chal- lenging for some novices [79, 82]. It is possible that students were overloaded by the complexity of these problems and, upon reach- ing a solution that works in a speciï¬c case, failed to attend to iden- tify the rest of the requirements. Pedagogical approaches that em- phasize full understanding of the problem handout [27, 70], or even brief quizzes requiring the student to read the problem in more de- tail, could be beneï¬cial [87].
In comparison with some prior studies that have reported data on syntax errors, our sample had relatively few: syntax errors fea- tured in only 8.0% of the help requests. This may be in part because we were dealing with code that students had chosen to submit for marking. These syntax errors were often jointly present with other types of issues.
|
2306.05715#55
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 55 |
# 5 Discussion
# Large Language Models Need More Benchmarks
In summary, the capabilities of LLMs are manifested in three distinct aspects Ouyang et al. (2022). And all three of these categories require benchmarks for automated evaluation. Although many benchmarks are constructed after the release of ChatGPT or GPT-4, LLMs still faced the problem of insufficient evaluation dimensions and insufficient evaluation detail because LLMs are more expressive than ever. Thus, we call upon the academic and industrial sectors to summarize hu- man knowledge and values, providing LLM development with more effective, comprehensive, and advanced benchmarks.
The first capability of LLMs is the understanding of knowledge, which encompasses memorization, reasoning, and abstraction Zhou et al. (2023). Currently, most works focus on enhancing the knowledge and understanding of LLMs through pre-training Fu et al. (2022). The proposal of Xiezhi is aiming at establishing a taxonomy for human knowledge and building evaluation criteria for this field. Although Xiezhi is already the most dimensional domain evaluation benchmark with largest volume of data, we currently offer only Chinese and English language version and lacks comprehensive coverage of knowledge from different cultures and industries. In the future, one of the critical improvements for Xiezhi lies in collecting more thorough and in-depth knowledge from various countries, nations, fields, and open source benchmarks in more languages.
|
2306.05783#55
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 55 |
⢠A uniï¬ed public benchmark is of an urgent need to provide reasonable and convincing evaluation protocols, since (1) the ï¬ne-grained cross comparison among exist- ing works remains vacant, and (2) it is quite expensive and difï¬cult to reproduce the experimental results of recom- mendation models combined with LLM.
⢠A customized large foundation model for recommenda- tion domains, which can take over control of the entire rec- ommendation pipeline, enabling a new level of automation in recommender systems.
References [Bao et al., 2023] Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. Tallrec: An effective and efï¬cient tuning framework to align large arXiv preprint language model with recommendation. arXiv:2305.00447, 2023.
[Borisov et al., 2023] Vadim Borisov, Kathrin Sessler, To- bias Leemann, Martin Pawelczyk, and Gjergji Kasneci. Language models are realistic tabular data generators. In The Eleventh International Conference on Learning Rep- resentations, 2023.
|
2306.05817#55
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 55 |
# 4.2.4 Labor and Creativity
Economic incentives to augment and not automate human labor, thought, and creativity should examine the ongoing effects generative AI systems have on skills, jobs, and the labor market.
# 4.2.4.1 Intellectual Property and Ownership
Rights to the training data and replicated or plagiarized work in addition to and rights to generated outputs are ongoing legal and policy discussions, often by specific modality. Impacts to people and society will necessarily coexist with impacts and development of intellectual property law.
What to Evaluate Determining whether original content has been used in training data depends on developer transparency or research on training data extraction [50]. Given the large sizes of training datasets, possible methods of evaluating original content inclusion could be through search and matching tools. In addition to unclear legal implications, the ambiguity of impacts on content ownership [239] makes evaluation difficult.
Mitigation and Intervention Similar to 4.2.1.3 Personal Privacy and Sense of Self, opt-in and opt-out mechanisms can protect intellectual property but depend on adherence. Regulation and stricter rules from a developer organization about training material will differ by modality. Ongoing lawsuits will set legal precedent [55]. Tools [215] are being developed to protect certain modalities from being used as training data.
# 4.2.4.2 Economy and Labor Market
|
2306.05949#55
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.07929
| 55 |
Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Voyager: An open-ended embodied agent with large language models. CoRR, abs/2305.16291, 2023a. doi: 10.48550/arXiv.2305.16291. URL https://doi.org/10.48550/ arXiv.2305.16291.
Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, and Denny Zhou. Self- consistency improves chain of thought reasoning in language models. CoRR, abs/2203.11171, 2022. doi: 10.48550/arXiv.2203.11171. URL https://doi.org/10.48550/arXiv.2203.11171.
|
2306.07929#55
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 56 |
3https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge
14
[System]
Please act as an impartial judge and evaluate the quality of the responses provided by two AI assistants to the user question displayed below. Your evaluation should consider correctness and helpfulness. You will be given assistant Aâs answer, and assistant Bâs answer. Your job is to evaluate which assistantâs answer is better. You should independently solve the user question step-by-step first. Then compare both assistantsâ answers with your answer. Identify and correct any mistakes. Avoid any position biases and ensure that the order in which the responses were presented does not influence your decision. Do not allow the length of the responses to influence your evaluation. Do not favor certain names of the assistants. Be as objective as possible. After providing your explanation, output your final verdict by strictly following this format: "[[A]]" if assistant A is better, "[[B]]" if assistant B is better, and "[[C]]" for a tie. [User Question] {question}
[User Question] {question} [The Start of Assistant Aâs Answer] {answer_a} [The End of Assistant Aâs Answer] [The Start of Assistant Bâs Answer] {answer_b} [The End of Assistant Bâs Answer]
|
2306.05685#56
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 56 |
Anecdotally, our dataset had several instances of the dreaded semicolon-in-conditional: if (foo); { ... }. This issue has been observed to take signiï¬cant amounts of time for students to ï¬x [3].
6 LIMITATIONS The particular features of our context limit the generalizability of our ï¬ndings. The course uses a relatively recent programming lan- guage (Dart), which the LLMs will not have âseenâ as much as some other programming languages. Moreover, the course is fully online, and its scope and student cohort are diï¬erent from many typical introductory programming courses at the university level; the is- sues that students request help with might thus diï¬er from other courses.
Relatedly, only a minority of code submissions had an associated help request. There are many possible explanations for this. For example, students may rely on other sources for help, such as the course materials or internet searches. It is also possible that the students who use the built-in help request functionality diï¬er from the general course population.
|
2306.05715#56
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 56 |
Except for knowledge evaluation, there are two other capabilities of LLMs that are in great need of benchmarks. One capacity is to understand and execute instructions, rendering LLM into a valuable artificial tool Aribandi et al. (2021); Hoffmann et al. (2022). Instruction fine-tuning is greatly involved in many works to enhance LLMâs instruction-following ability. However, the evaluation of LLM functionality largely relies on manual verification at present. Another is to align with human values,
9
which is essential for LLMs to evolve into artificial general intelligence (AGI) Bai et al. (2022); Perez et al. (2022). Numerous technical approaches for alignment have been proposed by companies like OpenAI and Claude, but many works have not aligned their models with human values due to the lack of direct improvement in downstream applications.
# Large Language Models Need Better Evaluation Methods
Current language models predominantly adopt generative approaches Zhao et al. (2023), and naturally, assessing these models presents inherent challenges Wang et al. (2023b). Most existing evaluation methods utilize multiple-choice questions to measure a generative modelâs understanding of knowl- edge and employ extraction techniques to obtain the modelâs answers Huang et al. (2023); Liu et al. (2023); Hendrycks et al. (2021).
|
2306.05783#56
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 56 |
[Brown et al., 2020] Tom Brown, Benjamin Mann, Nick Ry- der, Melanie Subbiah, Jared D Kaplan, Prafulla Dhari- wal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing sys- tems, 33:1877â1901, 2020.
[Carranza et al., 2023] Aldo Gael Carranza, Rezsa Farahani, Natalia Ponomareva, Alex Kurakin, Matthew Jagielski, and Milad Nasr. Privacy-preserving recommender systems with synthetic query generation using differentially private large language models. arXiv preprint arXiv:2305.05973, 2023.
[Chen et al., 2020] Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Zhangyang Wang, and Michael Carbin. The lottery ticket hypothesis for pre- trained bert networks. Advances in neural information pro- cessing systems, 33:15834â15846, 2020.
|
2306.05817#56
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 56 |
# 4.2.4.2 Economy and Labor Market
Key considerations about the impact of automation and AI on employment center on whether these technologies will generate new jobs or, in contrast, will lead to a large-scale worker displacement in the next future. Narratives about machines taking over the production of goods and services resurfaced periodically: from the early nineteenth-century Luddite movement against the introduction of the spinning jenny in textile manufacturing, to British farmersâ Swing Riots against mechanical threshers, to protests against the dial telephone, introduced in the U.S. during the Great Depression and responsible, according to its detractors, of mass unemployment among telephone operators [221].
|
2306.05949#56
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 56 |
[27] Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding, Ganqu Cui, Zheni Zeng, Yufei Huang, Chaojun Xiao, Chi Han, Yi Ren Fung, Yusheng Su, Huadong Wang, Cheng Qian, Runchu Tian, Kunlun Zhu, Shihao Liang, Xingyu Shen, Bokai Xu, Zhen Zhang, Yining Ye, Bowen Li, Ziwei Tang, Jing Yi, Yuzhang Zhu, Zhenning Dai, Lan Yan, Xin Cong, Yaxi Lu, Weilin Zhao, Yuxiang Huang, Junxi Yan, Xu Han, Xian Sun, Dahai Li, Jason Phang, Cheng Yang, Tongshuang Wu, Heng Ji, Zhiyuan Liu, and Maosong Sun. Tool learning with foundation models. CoRR, abs/2304.08354, 2023. doi: 10.48550/arXiv.2304.08354. URL https://doi.org/10.48550/arXiv.2304.08354.
|
2306.06070#56
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 56 |
ML models for reaction prediction and condition recommendation. The Open Reaction Database (ORD) [82] is a database of curated organic reactions. In the ORD, while reac- tion data are structured by the ORD schema, many of their procedures are also available as plain text. Interestingly, an LLM (e.g., OpenAIâs text-davinci-003) can, after ï¬ne- tuning on only 300 prompt-completion pairs, extract 93 % of the components from the free-text reaction description into valid JSONs (Figure 8). Such models might signiï¬- cantly increase the data available for training models on tasks such as predicting reaction conditions and yields. It is worth noting that all reaction data submitted to ORD are made available under the CC-BY-SA license, which makes ORD a suitable data source for ï¬ne-tuning or training an LLM to extract structured data from organic procedures. A recent study on gold nanorod growth procedures also demonstrated the ability of LLM in a similar task. [80] In contrast to the LIFT-based prediction of atomization energies re- ported in the ï¬rst section by the Berkeley-Madison team, parameter-eï¬cient ï¬ne-tuning of the open-source Alpaca model [83â85] using LoRA [47] did not yield a model that can
|
2306.06283#56
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 56 |
Zihao Wang, Shaofei Cai, Anji Liu, Xiaojian Ma, and Yitao Liang. Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. CoRR, abs/2302.01560, 2023b. doi: 10.48550/arXiv.2302.01560. URL https://doi.org/10.48550/ arXiv.2302.01560.
Christopher JCH Watkins and Peter Dayan. Q-learning. Machine learning, 8:279â292, 1992.
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, Quoc Le, and Denny Zhou. Chain of thought prompting elicits reasoning in large language models. CoRR, abs/2201.11903, 2022. URL https://arxiv.org/abs/2201.11903.
Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. Webshop: Towards scalable real-world web interaction with grounded language agents. CoRR, abs/2207.01206, 2022a. doi: 10.48550/arXiv.2207.01206. URL https://doi.org/10.48550/arXiv.2207.01206.
|
2306.07929#56
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 57 |
Figure 7: The chain-of-thought prompt for math and reasoning questions.
[System]
Please act as an impartial judge and evaluate the quality of the responses provided by two AI assistants to the user question displayed below. Your evaluation should consider correctness and helpfulness. You will be given a reference answer, assistant Aâs answer, and assistant Bâs answer. Your job is to evaluate which assistantâs answer is better. Begin your evaluation by comparing both assistantsâ answers with the reference answer Identify and correct any mistakes. Avoid any position biases and ensure that the order in which the responses were presented does not influence your decision. Do not allow the length of the responses to influence your evaluation. Do not favor certain names of the assistants. Be as objective as possible. After providing your explanation, output your final verdict by strictly following this format: "[[A]]" if assistant A is better, "[[B]]" if assistant B is better, and "[[C]]" for a tie.
User Question] {question} The Start of Reference Answer] {answer_ref} The End of Reference Answer] The Start of Assistant Aâs Answer] {answer_a} The End of Assistant Aâs Answer] The Start of Assistant Bâs Answer] {answer_b} The End of Assistant Bâs Answer]
Figure 8: The prompt for reference-guided pairwise comparison.
15
(â
[System]
|
2306.05685#57
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 57 |
A major limitation is that there are already newer LLMs than the ones we used. As we submitted this article for review, GPT-4 represented the state of the art, but we did not have programmatic access to it. Anecdotally, after receiving access to it, we have ob- served that GPT-4 outperforms GPT-3.5, to an extent, but does not fully eliminate the challenges highlighted in this article.
Our qualitative analysis employed a single coder, which is a threat to reliability.
Exploring the Responses of Large Language Models to Beginner Programmersâ Help Requests
In the present study, we relied on a single request to the model. However, LLM-based applications such as ChatGPT enable ongo- ing discussions with an evolving context, which is something we did not explore. In our future work, we are interested in studying a more conversational approach to providing feedback to students, which might more closely match the dialogue between a teaching assistant and a student, or a student and an LLM. One way to po- tentially achieve this could be to ï¬ne-tune the LLM to avoid giving correct answers and instead help the student arrive at the solution.
|
2306.05715#57
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 57 |
We argue that this evaluation approach is a sub-optimal approach. Since this approach requires models to possess the capability to answer multiple-choice questions, a skill seldom employed in real-world applications. For small LLMs or LLMs that have not been fine-tuned with multiple-choice data, such evaluation approaches fail to provide effective performance indicators.
In this paper, we propose evaluating models by using generative probability. While generative probability increases computational costs in comparison to directly answering questions, it yields a more accurate and effective assessment for LLMs unable to answer multiple-choice questions. Our study serves as an exploration of improved evaluation methodologies. In the future, we will consider incorporating a wider variety and diversity of evaluation approaches.
# 6 Conclusion
We introduced Xiezhi, a new benchmark that measures how well LLMs acquire and apply domain knowledge. By covering 516 subjects ranging from 13 categories with 249,587 questions, Xiezhi proposes a taxonomy of all human knowledge and assesses language understanding of the cutting- edge 47 LLMs in greatest breadth and depth among all previous benchmarks. We found that the SOTA LLMs have surpassed the average performance of practitioners in most domains. And there is a gap in generic domain knowledge understanding between large and small models. Our expansive test can help researchers pinpoint important shortcomings of models, making it easier to gain a clearer picture of modelâs capabilities in all domains.
10
# References
|
2306.05783#57
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 57 |
[Chen et al., 2023] Jiao Chen, Luyi Ma, Xiaohan Li, Nikhil Thakurdesai, Jianpeng Xu, Jason HD Cho, Kaushiki Nag, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. Knowledge graph completion models are few-shot learn- ers: An empirical study of relation labeling in e-commerce with llms. arXiv preprint arXiv:2305.09858, 2023.
[Chen, 2023] Zheng Chen. Palr: Personalization aware llms for recommendation. arXiv preprint arXiv:2305.07622, 2023.
Chris- takopoulou, Alberto Lalama, Cj Adams, Iris Qu, Yifat Amir, Samer Chucri, Pierce Vollucci, Fabio Soldo, Dina Bseiso, Sarah Scodel, et al. Large language models for user interest journeys. arXiv preprint arXiv:2305.15498, 2023.
[Cui et al., 2022] Zeyu Cui, Jianxin Ma, Chang Zhou, Jin- gren Zhou, and Hongxia Yang. M6-rec: Generative pre- trained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084, 2022.
|
2306.05817#57
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 57 |
Labor in system development such as crowdwork can encompass short-lived relations between inde- pendent contractors and their clients offers several advantages over traditional forms of employment. For example, companies can avoid overhead personnel costs (e.g., HR), while contract workers can decide how much, from where, and when to work. However, as contractors, crowdworkers are excluded from employment protective norms. As a result, they can be paid significantly less than minimum wage, have no access to healthcare benefits, are not subject to working time restrictions, and may not have access to holidays or sick leaves [188]. Further, crowdworkers are exposed to increasingly subtle forms of surveillance, which is becoming essential for implementing algorithmic forms of management, understood as "a diverse set of technological tools and techniques to remotely manage workforces [and] enable automated or semi-automated decision-making" [162]. The goal of full automation remains perpetually beyond reach since the line between what machines can and cannot solve is constantly redrawn by AI advancements. This phenomenon, the "paradox of automationâs last mile", is a self-propelling cycle in which every solution to automation problems creates new problems to be automated, and hence new demands for ghost workers [93].
16
|
2306.05949#57
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 57 |
[28] Nils Reimers and Iryna Gurevych. Sentence-bert: Sentence embeddings using siamese bert- networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11 2019. URL https://arxiv.org/ abs/1908.10084.
[29] Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettle- moyer, Nicola Cancedda, and Thomas Scialom. Toolformer: Language models can teach themselves to use tools. CoRR, abs/2302.04761, 2023. doi: 10.48550/arXiv.2302.04761. URL https://doi.org/10.48550/arXiv.2302.04761.
|
2306.06070#57
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 57 |
# construct valid JSONs.
21
c. TableToJson: Structured information from tables in scientiï¬c papers
The previous example shows how structured data can be extracted from plain text using LLMs. However, relevant information in the scientiï¬c literature is not only found in text form. Research papers often contain tables that collect data on material prop- erties, synthesis conditions, and results of characterization and experiments. Converting table information into structured formats is essential to enable automated data analy- sis, extraction, and integration into computational workï¬ows. Although some techniques could help in the process of extracting this information (performing OCR or parsing XML), converting this information in structured data following, for example, a speciï¬c JSON schema with models remains a challenge. The INCAR-CSIC team showed that the OpenAI text-davinci-003 model, when prompted with a desired JSON schema and the HyperText Markup Language (HTML) of a table contained in a scientiï¬c paper, can generate structured JSON with the data in the table.
|
2306.06283#57
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 57 |
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. CoRR, abs/2210.03629, 2022b. doi: 10.48550/arXiv.2210.03629. URL https://doi.org/10.48550/arXiv.2210.03629.
Danyang Zhang, Lu Chen, and Kai Yu. Mobile-Env: A universal platform for training and evaluation of mobile interaction. CoRR, abs/2305.08144, 2023. URL https://arxiv.org/abs/2305. 08144.
Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. Memorybank: Enhancing large language models with long-term memory. CoRR, abs/2305.10250, 2023. doi: 10.48550/arXiv. 2305.10250. URL https://doi.org/10.48550/arXiv.2305.10250.
13
|
2306.07929#57
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 58 |
Figure 8: The prompt for reference-guided pairwise comparison.
15
(â
[System]
Please act as an impartial judge and evaluate the quality of the responses provided by two AI assistants to the user question displayed below. You should choose the assistant that follows the userâs instructions and answers the userâs question better. Your evaluation should consider factors such as the helpfulness, relevance, accuracy, depth, creativity, and level of detail of their responses. Begin your evaluation by comparing the two responses and provide a short explanation. Avoid any position biases and ensure that the order in which the responses were presented does not influence your decision. Do not allow the length of the responses to influence your evaluation. Do not favor certain names of the assistants. Be as objective as possible. After providing your explanation, output your final verdict by strictly following this format: "[[A]]" if assistant A is better, "[[B]]" if assistant B is better, and "[[C]]" for a tie.
# <|The Start #4# User:
# of Assistant
# Aâs
# Conversation
# with User|>
# {question 1}
Assistant {answer 1}
##H#t
A:
#4#
# User:
# {question 2}
##H#t
# Assistant
A:
{answer 2} <|The End of
# Assistant
# Aâs
# Conversation
# with
# User|>
# <|The Start #4 User:
|
2306.05685#58
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 58 |
7 CONCLUSIONS In this study, we have taken a look at how two large language modelsâOpenAI Codex and GPT-3.5âperform in analyzing code that accompanies studentsâ help requests in a particular online course on programming basics.
Overall, we ï¬nd that the LLMsâ responses are usually sensible and potentially helpful (RQ2). GPT-3.5 in particular was good at identifying issues in student code. However, these LLMs cannot be counted on to identify all the issues present in a piece of code; they are also liable to report on âimaginaryâ non-issues and to mislead students. At least in this context and with these LLMs, output for- matting surfaced as a diï¬cult topic for the LLMs. Although the LLMs appear to perform best in English, responses in a fairly un- common non-English language were not far behind in quality.
|
2306.05715#58
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 58 |
10
# References
Aribandi, V., Tay, Y., Schuster, T., Rao, J., Zheng, H. S., Mehta, S. V., Zhuang, H., Tran, V. Q., Bahri, D., Ni, J., et al. (2021). Ext5: Towards extreme multi-task scaling for transfer learning. arXiv preprint arXiv:2111.10952.
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., McKinnon, C., et al. (2022). Constitutional ai: Harmlessness from ai feedback. arXiv preprint arXiv:2212.08073.
Biderman, S., Schoelkopf, H., Anthony, Q., Bradley, H., OâBrien, K., Hallahan, E., Khan, M. A., Purohit, S., Prashanth, U. S., Raff, E., Skowron, A., Sutawika, L., and van der Wal, O. (2023). Pythia: A suite for analyzing large language models across training and scaling.
|
2306.05783#58
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 58 |
[Dai et al., 2021] Xinyi Dai, Jianghao Lin, Weinan Zhang, Shuai Li, Weiwen Liu, Ruiming Tang, Xiuqiang He, Jianye Hao, Jun Wang, and Yong Yu. An adversarial imita- tion click model for information retrieval. In Proceedings of the Web Conference 2021, pages 1809â1820, 2021. [Dai et al., 2023] Sunhao Dai, Ninglu Shao, Haiyuan Zhao, Weijie Yu, Zihua Si, Chen Xu, Zhongxiang Sun, Xiao Zhang, and Jun Xu. Uncovering chatgptâs capabilities in recommender systems. arXiv preprint arXiv:2305.02182, 2023.
[Devlin et al., 2018] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. arXiv preprint arXiv:1810.04805, 2018.
[Ding et al., 2020] Ming Ding, Chang Zhou, Hongxia Yang, and Jie Tang. Cogltx: Applying bert to long texts. Advances in Neural Information Processing Systems, 33:12792â12804, 2020.
|
2306.05817#58
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 58 |
16
What to Evaluate Long-term impact on the global economy is unclear and depends on industry decisions to use generative AI to augment or automate jobs. Factors to be evaluated include un- employment rates, salaries for a given skill or task, economic class divisions, and overall cost of services. [57] argues that the substitution of labor for capital, as in the case of the introduction of labor-substituting technologies, might lead to cost cuts in the short term. The externalities2 of AI and automation, however, can be detrimental in the long term and could lead to unemployment, smaller tax bases, and economic inequality between skilled workers and a growing underclass. [136] offers a complementary perspective when arguing how AI in the workplace can stimulate competition, drive prices down, and have a net-positive effect on employment. For specific tasks, evaluating quality of generated output compared to human output can give signal to the likelihood of a generative AI system replacing human labor [212].
|
2306.05949#58
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 58 |
[30] Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. Hug- ginggpt: Solving AI tasks with chatgpt and its friends in huggingface. CoRR, abs/2303.17580, 2023. doi: 10.48550/arXiv.2303.17580. URL https://doi.org/10.48550/arXiv.2303. 17580.
[31] Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, and Percy Liang. World of Bits: An Open-Domain Platform for Web-Based Agents. In Proceedings of the 34th International Conference on Machine Learning, pages 3135â3144. PMLR, July 2017.
[32] Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. ALFRED: A benchmark for interpreting grounded In 2020 IEEE/CVF Conference on Computer Vision and instructions for everyday tasks. Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pages 10737â10746.
13
|
2306.06070#58
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 58 |
First, the OpenAI text-davinci-003 model was directly used to generate JSON objects from the table information. This approach was applied to several examples using tables collected from papers on diï¬erent research topics within the ï¬eld of chemistry [86â 92]. The accuracy for those diï¬erent examples, calculated as the percentage of schema values generated correctly, is shown in Figure 9. When the OpenAI model was prompted with the table and desired schema to generate a JSON object, it worked remarkably well in extracting the information from each table cell and inserting it at the expected place in the schema. As output, it provided a valid JSON object with a 100 % success rate of error-free generated values in all the studied examples. However, in some examples, the model did not follow the schema.
|
2306.06283#58
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 58 |
13
Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, Yu Qiao, Zhaoxiang Zhang, and Jifeng Dai. Ghost in the minecraft: Generally capable agents for open-world environments via large language models with text-based knowledge and memory. CoRR, abs/2305.17144, 2023. doi: 10.48550/arXiv.2305.17144. URL https://doi.org/10.48550/arXiv.2305.17144.
# A Details about the observation formats
Instruction: i would like a 3 ounce bottle of bright citrus deodorant for sensitive skin, and price lower than 40.00 dollars [Back to Search] Page 1 (Total results: 50) [Next >] [BO78GWRC1J]
Bright Citrus Deodorant by Earth Mama | Natural and Safe for Sensitive Skin, reid and Breastfeeding, Contains Organic Calendula 3-Ounce 10.99
[BO78GTKVXY]
Ginger Fresh Deodorant by Earth Mama | Natural and Safe for Sensitive Skin, Pregnancy and Breastfeeding, Contains Organic Calendula 3-Ounce $10.99
[BO8KBVJ4XN]
|
2306.07929#58
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 59 |
# Assistant
A:
{answer 2} <|The End of
# Assistant
# Aâs
# Conversation
# with
# User|>
# <|The Start #4 User:
# of Assistant
# Bâs
# Conversation
# with User|>
# {question 1}
Assistant {answer 1}
##H#
B:
#4#
# User:
# {question 2}
##H#t
# Assistant
B:
{answer 2} <|The End of XX
# Assistant
# Bâs
# Conversation
# with
# User|>
# Figure 9: The prompt for multi-turn pairwise comparison.
16
>)
# S
[System]
Please act as an impartial judge and evaluate the quality of the response provided by an AI assistant to the user question. Your evaluation should consider correctness and helpfulness. You will be given a reference answer and the assistant's answer. You evaluation should focus on the assistant's answer to the second question. Begin your evaluation by comparing the assistant's answer with the reference answer. Identify and correct any mistakes. Be as objective as possible. After providing your explanation, you must rate the response on a scale of 1 to 10 by strictly following this format: â[[rating]]", for example: âRating: [[5]]".
# <|The Start #4# User:
# of
# Reference Answer|>
# {question_1}
# Reference {ref_answer_1}
#####
# answer:
#4
|
2306.05685#59
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 59 |
We see LLMs as a potentially excellent supplement for program- ming teachers and teaching assistants, available at scale to serve the ever-increasing numbers of programming students. Not as a replacement for teachers, however. If we dismiss for a moment the risks of anthropomorphisms, we may describe an LLM as a be- ginner programmerâs quick-thinking, often helpful but unreliable tutor friend, who has plenty of experience with code but less of an understanding of good pedagogy, and who has a penchant for blurting out model solutions even when you directly ask them not to.
Our study also presented us with a window into studentsâ help- seeking behavior (RQ1). We found that: students infrequently asked for help even when their code submissions were failing; most is- sues involved program logic or input/output; and the I/O issues might stem from worked examples in the course materials. These ï¬ndings, too, are speciï¬c to the studied context and their general- izability remains to be determined.
|
2306.05715#59
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 59 |
Bisk, Y., Zellers, R., Gao, J., Choi, Y., et al. (2020). Piqa: Reasoning about physical commonsense in natural language. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 7432â7439.
Black, S., Biderman, S., Hallahan, E., Anthony, Q., Gao, L., Golding, L., He, H., Leahy, C., McDonell, K., Phang, J., Pieler, M., Prashanth, U. S., Purohit, S., Reynolds, L., Tow, J., Wang, B., and Weinbach, S. (2022). Gpt-neox-20b: An open-source autoregressive language model.
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023). Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712.
|
2306.05783#59
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 59 |
[Ding et al., 2021] Hao Ding, Yifei Ma, Anoop Deoras, Yuyang Wang, and Hao Wang. Zero-shot recommender systems. arXiv preprint arXiv:2105.08318, 2021.
[Friedman et al., 2023] Luke Friedman, Sameer Ahuja, David Allen, Terry Tan, Hakim Sidahmed, Changbo Long, Jun Xie, Gabriel Schubiner, Ajay Patel, Harsh Lara, et al.
Leveraging large language models in conversational rec- arXiv preprint arXiv:2305.07961, ommender systems. 2023.
|
2306.05817#59
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 59 |
A task-polarization model [22] shows how AI can potentially widen the gap between high and low- wage occupations at the expense of the middle tier. [14] shows how technological advancements have historically increased earning inequality between education, sex, race, and age groups. Therefore, looking at the overall growth or decline of the labor market might mislead about the real impact of AI; AI might be displacing labor and yet, at the same time, creating new jobs, thus making it challenging to fully evaluate its implications unless we investigate into the kind of jobs that are being created and destroyed.
See 4.1.7 Data and Content Moderation Labor for evaluating human labor in the research, develop- ment, and deployment process.
Mitigation and Intervention In additional to labor protection laws, more inclusive design pro- cesses, as argued by [214] can open technological decisions to democratic participation as a way to steer innovation in socially desirable directions.
|
2306.05949#59
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 59 |
13
Computer Vision Foundation / IEEE, 2020. doi: 10.1109/CVPR42600.2020.01075. URL https://openaccess.thecvf.com/content_CVPR_2020/html/Shridhar_ALFRED_ A_Benchmark_for_Interpreting_Grounded_Instructions_for_Everyday_Tasks_ CVPR_2020_paper.html.
[33] Chan Hee Song, Jiaman Wu, Clayton Washington, Brian M. Sadler, Wei-Lun Chao, and Yu Su. Llm-planner: Few-shot grounded planning for embodied agents with large language models. CoRR, abs/2212.04088, 2022. doi: 10.48550/arXiv.2212.04088. URL https://doi.org/10. 48550/arXiv.2212.04088.
|
2306.06070#59
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 59 |
To potentially address this problem the team utilized the jsonformer approach. This tool reads the keys from the JSON schema and only generates the value tokens, guaran- teeing the generation of a syntactically valid JSON (corresponding to the desired schema) by the LLM [93, 94]. Using an LLM without such a decoding strategy cannot guarantee that valid JSON outputs are produced. With the jsonformer approach, in most cases, by using a simple descriptive prompt about the type of input text, structured data can be obtained with 100 % correctness of the generated values. In one example, an accuracy of 80 % was obtained due to errors in the generation of numbers in scientiï¬c notation. For a table with more complex content (long molecule names, hyphens, power numbers, subscripts, and superscripts,. . . ) the team achieved an accuracy of only 46 %. Most of
22
these issues could be solved by adding a speciï¬c explanation in the prompt, increasing the accuracy to 100 % in most cases.
|
2306.06283#59
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 59 |
[BO8KBVJ4XN]
Barrel and Oak - Aluminum-Free Deodorant, Deodorant for Men, Essential Oil-Based Scent, 24-Hour Odor Protection, Cedar & Patchouli Blend, Gentle on Sensitive Skin (Mountain Sage, 2.7 0z, 2-Pack) $15.95
Figure 5: Example of the observation of WebShop
The observation of WebShop is simplified based on the text_rich format of WebShop [Yao et al., 2022a] in exactly the same way with Yao et al. [2022b]. Specifically, the HTML markups are omitted, and the buttons are represented in [text] or [[text]] instead of the complicated [button] text [button_] or [clicked button] text [clicked button_]. Furthermore, the number of displayed search results per page is clipped to 3 instead of 10. An example is shown in Figure 5.
The observation of WikiHow is represented in exactly the same way with Zhang et al. [2023]. Specifically, the page is converted into a sequence of HTML elements corresponding to the visible leaf nodes on the Android ⢠view hierarchy (VH). The node classes are converted into HTML tags and a few VH properties are converted into similar HTML attributes. The text property is converted to the text content of the common HTML element or the value attribute of the input element.
|
2306.07929#59
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 60 |
# <|The Start #4# User:
# of
# Reference Answer|>
# {question_1}
# Reference {ref_answer_1}
#####
# answer:
#4
# User:
# {question_2}
#####
# Reference
# answer:
# {ref_answer_2} <|The End of Reference Answer|>
# <|The Start #4# User:
# of Assistant
# A's
# Conversation
# with User|>
# {question_1}
##H#t
# Assistant
A:
# {answer_1}
#4
# User:
# {question_2}
##H#t
# Assistant
A:
{answer_2} q <|The End of
# Assistant
# A's
# Conversation
# with
# User|>
Figure 10: The prompt for reference-guided multi-turn single-answer grading.
17
# B Case Study
We list several case studies. The examples are generated by gpt-4-0314. They may not be fully reproducible with future GPT-4 versions.
|
2306.05685#60
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 60 |
The capabilities and availability of large language models mean that they will be a part of programming education in the futureâ they are already a part of it today. Computing educators and com- puting education researchers must ï¬nd out how to employ these tools productively and to avoid their pitfalls. Future programming students might beneï¬t not only from generic LLMs such as the ones we studied but also from custom LLMs designed and taught to serve the needs of student programmers. We hope that our re- search is a step towards that goal.
ACKNOWLEDGMENTS We are grateful for the grant from the Ulla Tuominen Foundation to the second author.
ICER â23 V1, August 7â11, 2023, Chicago, IL, USA
REFERENCES [1] Alireza Ahadi, Raymond Lister, Heikki Haapala, and Arto Vihavainen. 2015. Ex- ploring machine learning methods to automatically identify students in need of assistance. In Proceedings of the eleventh annual international conference on international computing education research. 121â130.
|
2306.05715#60
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 60 |
Chiang, W.-L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J. E., Stoica, I., and Xing, E. P. (2023). Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, E., Wang, X., Dehghani, M., Brahma, S., et al. (2022). Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416.
Conover, M., Hayes, M., Mathur, A., Meng, X., Xie, J., Wan, J., Shah, S., Ghodsi, A., Introducing the worldâs Wendell, P., Zaharia, M., and Xin, R. (2023). first truly open instruction-tuned llm. https://www.databricks.com/blog/2023/04/12/ dolly-first-open-commercially-viable-instruction-tuned-llm.
|
2306.05783#60
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 60 |
Leveraging large language models in conversational rec- arXiv preprint arXiv:2305.07961, ommender systems. 2023.
[Fu et al., 2023a] Junchen Fu, Fajie Yuan, Yu Song, Zheng Yuan, Mingyue Cheng, Shenghui Cheng, Jiaqi Zhang, Jie Wang, and Yunzhu Pan. Exploring adapter-based transfer learning for recommender systems: Empirical studies and practical insights. arXiv preprint arXiv:2305.15036, 2023. [Fu et al., 2023b] Lingyue Fu, Jianghao Lin, Weiwen Liu, Ruiming Tang, Weinan Zhang, Rui Zhang, and Yong Yu. An f-shape click model for information retrieval on multi- block mobile pages. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Min- ing, pages 1057â1065, 2023.
[Gao et al., 2023] Yunfan Gao, Tao Sheng, Youlin Xiang, Yun Xiong, Haofen Wang, and Jiawei Zhang. Chat- rec: Towards interactive and explainable llms-augmented recommender system. arXiv preprint arXiv:2303.14524, 2023.
|
2306.05817#60
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 60 |
For human labor in AI development, a central challenge is discerning genuinely self-employed crowd-contractors from salaried workers and platformsâ responsibilities within the multiparty rela- tionship between crowdworkers and crowdsourcers. Traditionally, crowd platforms (such as Amazon Mechanical Turk, Clickwork, and Appen) have positioned themselves as mere conduits through which client companies (crowdsourcers) can publicize their tasks and hire crowdworkers. Because of the nature of crowdsourced workâusually small tasks requiring only several minutes to completeâit is not uncommon for crowdworkers to work for hundreds of different companies in a week [79]. Crowdworkers have commonly been framed as contractors for crowdsourcing companies, while platforms maintain a neutral position and profit from service fees applied to each transaction.
|
2306.05949#60
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 60 |
[34] Yu Su, Ahmed Hassan Awadallah, Madian Khabsa, Patrick Pantel, Michael Gamon, and Mark J. Encarnación. Building natural language interfaces to web apis. In Ee-Peng Lim, Marianne Winslett, Mark Sanderson, Ada Wai-Chee Fu, Jimeng Sun, J. Shane Culpepper, Eric Lo, Joyce C. Ho, Debora Donato, Rakesh Agrawal, Yu Zheng, Carlos Castillo, Aixin Sun, Vincent S. Tseng, and Chenliang Li, editors, Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore, November 06 - 10, 2017, pages 177â186. ACM, 2017. doi: 10.1145/3132847.3133009. URL https://doi.org/10.1145/3132847. 3133009.
[35] Liangtai Sun, Xingyu Chen, Lu Chen, Tianle Dai, Zichen Zhu, and Kai Yu. META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI, November 2022.
|
2306.06070#60
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 60 |
22
these issues could be solved by adding a speciï¬c explanation in the prompt, increasing the accuracy to 100 % in most cases.
Overall, both approaches performed well in generating the JSON format. The OpenAI text-davinci-003 model could correctly extract structured information from tables and give a valid JSON output, but it cannot guarantee that the outputs will always follow the provided schema. Jsonformer may present problems when special characters need to be generated, but most of these issues could be solved with careful prompting. These results show that LLMs can be a useful tool to help to extract scientiï¬c information in tables and convert it into a structured form with a ï¬xed schema that can be stored in a database, which could encourage the creation of more topic-speciï¬c databases of research results.
|
2306.06283#60
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 60 |
# B Lookup table of the pattern-based similarity functions
# B.1 Lookup table of the page similarity function of WebShop
We inspected the pages from WebShop and categorized them into 4 patterns as depicted in Table 9.
The similarity lookup table is defined in Table 10.
# B.2 Lookup table of the instruction similarity function of WikiHow
We inspected the step instructions from WikiHow and categorized them into 6 patterns as depicted in Table 11.
14
# Table 9: Patterns of WebShop pages
Pattern Description search The page to search for an item itemlisting The page listing the search results item others The information page of a specific item The item description page, item feature page, and review page
Table 10: Lookup table of the page similarity of WebShop
search itemlisting item others search 1 0 0 0 itemlisting 0 1 0 0 item others 0 0 1 0.3 0 0 0.3 1
The similarity lookup table is defined in Table 12.
# C Hyper-parameters
The discount factor γ to accumulate the rewards in the formula of Q value is 1, which means no discounts are considered. The learning rate α is 1/N where N denotes the times the value is updated. Such a learning rate is chosen, as the tested environments are stationary and each estimation to the value is expected to be equally weighted. The similarity weight factor λ is 0.5, indicating two parts of the similarity function contribute equally.
|
2306.07929#60
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 61 |
Question: What are some business etiquette norms when doing business in Japan? Assistant A: Assistant B: Here are some business etiquette norms to keep When doing business in Japan, it is important to be in mind when doing business in Japan: aware of and respect the countryâs business 1. Bowing: Bowing is a common greeting in etiquette norms. Some of these norms include: Japan. It is a sign of respect and should 1. Greetings: A handshake and bow is the standard be reciprocated. greeting in Japan. It is important to bow deeply 2. Business cards: Business cards are and to offer a firm handshake. exchanged at the beginning of a meeting. It 2. Business cards: In Japan, business cards are is important to receive and give business exchanged after the initial greeting. It is cards with both hands and to take a moment important to handle the card with respect and to to read the card before putting it away. read it carefully before placing it on the 3. Punctuality: Being on time is important in table. Japan. Arrive a few minutes early to show 3. Meetings: Meetings in Japan are typically formal respect for your colleagues. and conducted in a hierarchical manner. It is 4. Dress code: Dress conservatively and important to
|
2306.05685#61
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 61 |
[2] Kirsti M Ala-Mutka. 2005. A survey of automated assessment approaches for programming assignments. Computer science education 15, 2 (2005), 83â102. [3] Amjad Altadmri and Neil CC Brown. 2015. 37 million compilations: Investigat- ing novice programming mistakes in large-scale student data. In Proc. of the 46th ACM Technical Symposium on Computer Science Education. 522â527.
[4] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural ma- arXiv preprint chine translation by jointly learning to align and translate. arXiv:1409.0473 (2014).
[5] Brett A Becker. 2016. A new metric to quantify repeated compiler errors for novice programmers. In Proceedings of the 2016 ACM Conference on Innovation and Technology in Computer Science Education. 296â301.
|
2306.05715#61
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 61 |
Du, Z., Qian, Y., Liu, X., Ding, M., Qiu, J., Yang, Z., and Tang, J. (2022). Glm: General language model pretraining with autoregressive blank infilling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 320â335.
Fu, Y., Peng, H., and Khot, T. (2022). How does gpt obtain its ability? tracing emergent abilities of language models to their sources. Yao Fuâs Notion.
Fu, Y., Peng, H., Ou, L., Sabharwal, A., and Khot, T. (2023). Specializing smaller language models towards multi-step reasoning. arXiv preprint arXiv:2301.12726.
H2O.ai (2023). h2ogpt - the worldâs best open source gpt. https://github.com/h2oai/h2ogpt.
|
2306.05783#61
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 61 |
[Geng et al., 2022] Shijie Geng, Shuchang Liu, Zuohui Fu, Yingqiang Ge, and Yongfeng Zhang. Recommendation as language processing (rlp): A uniï¬ed pretrain, personalized In Proceedings of the prompt & predict paradigm (p5). 16th ACM Conference on Recommender Systems, pages 299â315, 2022.
[Geng et al., 2023] Shijie Geng, Juntao Tan, Shuchang Liu, Zuohui Fu, and Yongfeng Zhang. Vip5: Towards mul- timodal foundation models for recommendation. arXiv preprint arXiv:2305.14302, 2023.
[Guo et al., 2017] Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. a factorization-machine based neural network for ctr predic- tion. arXiv preprint arXiv:1703.04247, 2017.
|
2306.05817#61
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 61 |
To protect crowdworkers, regulators are proposals new rules For instance, Californiaâs Bill AB-5 [5] advances new rules for determining whether a worker is an independent contractor or should be treated, instead, as an employee. Europe might follow suit soon with the introduction of the proposed Directive 2021/0414(COD) [7], which sets precise criteria for determining platform workersâ employment status and access to labor protection rights in addition to transparency requirements about employeesâ working conditions. The Directive dovetails with the proposed AI Act (COM(2021) 206 final) [74] that aims to ensure that AI algorithms employed in the EU respect fundamental human rights. The proposed AI Act also requires high-risk AI systems to fulfill stringent transparency and data accessibility requirements and imposes platforms to disclose to workers the criteria and the data used in automated decision-making systems.
# 4.2.5 Ecosystem and Environment
Impacts at a high-level, from the AI ecosystem to the Earth itself, are necessarily broad but can be broken down into components for evaluation.
# 4.2.5.1 Widening Resource Gaps
|
2306.05949#61
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 61 |
[36] Bailin Wang, Richard Shin, Xiaodong Liu, Oleksandr Polozov, and Matthew Richardson. RAT- SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7567â7578, Online, 2020. Association for Computational Linguistics. doi: 10.18653/v1/2020.acl-main.677.
[37] Kyle Williams, Seyyed Hadi Hashemi, and Imed Zitouni. Automatic task completion flows In Benjamin Piwowarski, Max Chevalier, Ãric Gaussier, Yoelle Maarek, from web apis. Jian-Yun Nie, and Falk Scholer, editors, Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, Paris, France, July 21-25, 2019, pages 1009â1012. ACM, 2019. doi: 10.1145/3331184.3331318. URL https://doi.org/10.1145/3331184.3331318.
|
2306.06070#61
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 61 |
text-davinci-003 text-davinci-003 (schema in prompt) + jsonformer prompt = "Generate a JSON object extracting the information from this table in html code: â + HTML_table + "Generate the JSON result with the following JSON schema and give only the JSON as output: â + JSON_schema JSON follows schema % values extracted ok JSON follows schema % values extracted ok carbon materials for CO, adsorption v 100% v 100% MOFs properties v 100% v 100% supercapacitor performance v 100% v 100% catalysts for CO, conversion xmav 100% v 94% biomass properties v 100% v 100% anode materials for SOFCs xmav 100% v 80% =100% perovskite cathodes for SOFCs v 100% v 46% = 60% 86-100%
|
2306.06283#61
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 61 |
# D Capability evolving of REMEMBERER
(a) Capability evolving on WebShop (b) Capability evolving on WikiHow
# Avg Score
Figure 6: Performance on a random subset at epochs 1, 3, 5, and 10
We further conducted experiments to see how the capability of REMEMBERER evolves during training. Owing to the limit of budgets, a subset of only 20 tasks is sampled from the full test set. We visualize the performance on the subset of REMEMBERER at epochs 1, 5, and 10. The performance at epoch 3, which is used for the experiments in the main paper, is visualized as well. The visualization is available in Figure 6. It can be seen that the performance of REMEMBERER improves during the training procedure. However, there seems to be a saturation for the performance, which may be attributed to the limited number of the active exemplars and training tasks. The saturation of the average reward comes later than that of the success rate. This fact indicates that REMEMBERER can still seize more rewards through training on several unsuccessful tasks even the success rate has
15
# Table 11: Patterns of WikiHow instructions
Pattern Name Pattern Template search article author category reference about Search an article to learn . . . Access the article . . . Check the author page of . . . Access the page of category . . . Check the reference list. Access the about page . . .
|
2306.07929#61
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 62 |
in Japan are typically formal respect for your colleagues. and conducted in a hierarchical manner. It is 4. Dress code: Dress conservatively and important to address people by their titles and professionally. Men should wear dark suits to avoid direct eye contact. and ties, while women should wear 4. Punctuality: Punctuality is highly valued in conservative business attire. Japan. It is important to arrive on time for 5. Language: Learn a few basic Japanese meetings and to be prepared in advance. phrases to show respect for the culture. It 5. Gift giving: Gift giving is a common practice in is also important to speak clearly and Japan, but it is important to be mindful of the avoid using slang or idioms. occasion and the relationship. Avoid giving 6. Gift giving: Gift giving is a common gifts that are considered too personal or practice in Japan. Bring a small gift, such extravagant. as a box of chocolates or a small souvenir 6. Dining: Dining is an important part of doing from your home country. business in Japan. It is important to be aware 7. Dining etiquette: When dining with of the proper table manners and to avoid colleagues, wait for the host to begin slurping or making loud noises
|
2306.05685#62
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 62 |
[6] Brett A. Becker, Paul Denny, James Finnie-Ansley, Andrew Luxton-Reilly, James Prather, and Eddie Antonio Santos. 2022. Programming Is Hard â Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation. [7] Brett A Becker, Paul Denny, Raymond Pettit, Durell Bouchard, Dennis J Bouvier, Brian Harrington, Amir Kamil, Amey Karkare, Chris McDonald, Peter-Michael Osera, et al. 2019. Compiler error messages considered unhelpful: The landscape of text-based programming error message research. Proceedings of the working group reports on innovation and technology in computer science education (2019), 177â210.
[8] Gary D Borich Borich. 2005. Educational psychology: A contemporary approach. [9] Neil CC Brown and Amjad Altadmri. 2014. Investigating novice programming mistakes: Educator beliefs vs. student data. In Proceedings of the tenth annual conference on International computing education research. 43â50.
[10] Neil CC Brown and Amjad Altadmri. 2017. Novice Java programming mistakes: Large-scale data vs. educator beliefs. ACM Transactions on Computing Education (TOCE) 17, 2 (2017), 1â21.
|
2306.05715#62
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 62 |
Hendrycks, D., Basart, S., Kadavath, S., Mazeika, M., Arora, A., Guo, E., Burns, C., Puranik, S., He, H., Song, D., et al. (2021). Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938.
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., de Las Casas, D., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022). An empirical analysis of compute-optimal large language model training. Advances in Neural Information Processing Systems, 35:30016â30030.
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2021). Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.
|
2306.05783#62
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 62 |
[He et al., 2022] Junda He, Bowen Xu, Zhou Yang, Dong- Gyun Han, Chengran Yang, and David Lo. Ptm4tag: sharpening tag recommendation of stack overï¬ow posts In Proceedings of the 30th with pre-trained models. IEEE/ACM International Conference on Program Com- prehension, pages 1â11, 2022.
[Hegselmann et al., 2023] Stefan Hegselmann, Alejandro Buendia, Hunter Lang, Monica Agrawal, Xiaoyi Jiang, and David Sontag. Tabllm: Few-shot classiï¬cation of tab- In International ular data with large language models. Conference on Artiï¬cial Intelligence and Statistics, pages 5549â5581. PMLR, 2023.
[Hou et al., 2022] Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, and Ji-Rong Wen. To- wards universal sequence representation learning for rec- In Proceedings of the 28th ACM ommender systems. SIGKDD Conference on Knowledge Discovery and Data Mining, pages 585â593, 2022.
|
2306.05817#62
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 62 |
# 4.2.5.1 Widening Resource Gaps
As described in section Financial Costs, the high financial and resource costs necessarily excludes groups who do not have the resources to train, evaluate, or host models. The infrastructure needed to contribute to generative AI research and development leads to widening gaps which are notable among sectors, such as between industry and academia [145], or among global powers and countries [19].
2Externalities broadly refer to the unanticipated effects of economic activities on the social environment.
17
Access and Benefit Distribution Ability to contribute to and benefit from a system depends on ability to engage with a system, which in turn depends on the openness of the system, the system application, and system interfaces. Level of openness and access grapples with tensions of misuse and risk. Increasing trends toward system closedness [227] is shifting access distribution.
Geographic and Regional Activity Concentration In the field of AI as a whole, top AI research institutions from 1990-2014 have concentrated in the U.S. [164]. More recent data highlights the U.S., EU, and China as primary hubs [198]. Even within the U.S. AI activity concentrates in urban, coastal areas [154].
|
2306.05949#62
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 62 |
[38] Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. Transformers: State-of-the- art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38â45, Online, October 2020. Association for Computational Linguistics. URL https://www.aclweb.org/anthology/ 2020.emnlp-demos.6.
[39] Nancy Xu, Sam Masling, Michael Du, Giovanni Campagna, Larry Heck, James A. Landay, and Monica S. Lam. Grounding open-domain instructions to automate web support tasks. In North American Chapter of the Association for Computational Linguistics, 2021.
|
2306.06070#62
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 62 |
Figure 9: TableToJson. Results of the structured JSON generation of tables contained in scientiï¬c articles. Two approaches are compared: (i) the use of an OpenAI model prompted with the desired JSON schema, and (ii) the use of an OpenAI model together with jsonformer. In both cases, JSON objects were always obtained. The output of the OpenAI model did not always follow the provided schema, although this might be solved by modifying the schema. The accuracy of the results from the jsonformer approach used with OpenAI models could be increased (as shown by the blue arrows) by solving errors in the generation of power numbers and special characters with a more detailed prompt. The results can be visualized in this demo app: https://vgvinter-tabletojson-app-kt5aiv.streamlit.app/
d. AbstractToTitle & TitleToAbstract: text summarization and text generation
Technical writing is a challenging task that often requires presenting complex abstract ideas in limited space. For this, frequent rewrites of sections are needed, in which LLMs could assist domain experts. Still, evaluating their ability to generate text such as a scientiï¬c paper is essential, especially for chemistry and materials science applications.
23
|
2306.06283#62
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 62 |
Table 12: Lookup table of the instruction similarity of WikiHow author 0 0.3 1 0.8 0.3 0.3
already saturated. In other words, the hard tasks benefit more from the later phase of training than the easy tasks. Besides, REMEMBERER reaches saturation on WebShop earlier than on WikiHow. To give an explanation, the number of the experiences in the memory after each training epoch is inspected. As shown in Figure 7, there are much fewer new experiences added into the memory in the later epochs for WebShop than for WikiHow. The certain reason may be due to the specific training set or some internal characteristics of the task domain, which will be further investigated in the future work.
# E Q function fitting ability of REMEMBERER
Ablation study in the main paper has demonstrated that n-step bootstrapping manages to improve precision of the learned Q values in the memory. This section will give further discussion about over-estimation of learned Q values in the memory and whether the LLM can learn the certain Q function through in-context learning (ICL).
|
2306.07929#62
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 63 |
7. Dining etiquette: When dining with of the proper table manners and to avoid colleagues, wait for the host to begin slurping or making loud noises while eating. eating before you start. Use chopsticks 7. Communication: Communication in Japan is correctly and avoid leaving food on your typically indirect and reserved. It is important plate. to listen carefully and to avoid confrontational language. Remember, showing respect for Japanese culture and customs is key to building strong business Overall, it is important to be respectful, relationships in Japan. punctual, and mindful of hierarchy when doing business in Japan. GPT-4 Judgment (when A is placed in the first position): Both Assistant A and Assistant B provide helpful and relevant information about business etiquette norms in Japan. However, Assistant Aâs answer is more detailed and organized, covering a wider range of topics such as dress code and language, which are not mentioned in Assistant Bâs response. Assistant A also provides more specific advice on how to handle certain situations, such as exchanging business cards and dining etiquette. Therefore, Assistant Aâs answer is more comprehensive and useful for someone looking to understand Japanese business etiquette. GPT-4 Judgment (when B is placed in the first position):
|
2306.05685#63
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 63 |
[11] Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877â1901.
[12] Ruth Butler. 1998. Determinants of help seeking: Relations between perceived reasons for classroom help-avoidance and help-seeking behaviors in an experi- mental context. J. of Educ. Psychology 90, 4 (1998).
[13] Adam S Carter, Christopher D Hundhausen, and Olusola Adesope. 2015. The normalized programming state model: Predicting student performance in com- puting courses based on programming behavior. In Proceedings of the eleventh annual international conference on international computing education research. 141â150.
[14] Paul Denny, Viraj Kumar, and Nasser Giacaman. 2022. Conversing with Copi- lot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Lan- guage.
|
2306.05715#63
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 63 |
Hu, Z., Lan, Y., Wang, L., Xu, W., Lim, E.-P., Lee, R. K.-W., Bing, L., and Poria, S. (2023). Llm- adapters: An adapter family for parameter-efficient fine-tuning of large language models. arXiv preprint arXiv:2304.01933.
11
Huang, L., Bras, R. L., Bhagavatula, C., and Choi, Y. (2019). Cosmos qa: Machine reading comprehension with contextual commonsense reasoning. arXiv preprint arXiv:1909.00277.
Huang, Y., Bai, Y., Zhu, Z., Zhang, J., Zhang, J., Su, T., Liu, J., Lv, C., Zhang, Y., Lei, J., et al. (2023). C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. arXiv preprint arXiv:2305.08322.
Ji, Y., Deng, Y., Gong, Y., Peng, Y., Niu, Q., Zhang, L., Ma, B., and Li, X. (2023a). Exploring the impact of instruction data scaling on large language models: An empirical study on real-world use cases. arXiv preprint arXiv:2303.14742.
|
2306.05783#63
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 63 |
Julian McAuley, and Wayne Xin Zhao. Learning vector- quantized item representation for transferable sequential recommenders. In Proceedings of the ACM Web Confer- ence 2023, pages 1162â1171, 2023.
Junjie Zhang, Zihan Lin, Hongyu Lu, Ruobing Xie, Julian McAuley, and Large language models are zero- Wayne Xin Zhao. shot rankers for recommender systems. arXiv preprint arXiv:2305.08845, 2023.
[Hu et al., 2021] Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021. [Hua et al., 2023a] Wenyue Hua, Yingqiang Ge, Shuyuan Xu, Jianchao Ji, and Yongfeng Zhang. Up5: Unbi- ased foundation model for fairness-aware recommenda- tion. arXiv preprint arXiv:2305.12090, 2023.
|
2306.05817#63
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 63 |
What to Evaluate Evaluation should first determine AI-specific resources then tracking trends by sector and region. To determine and evaluate level of access, first components of access should be established. This includes technical details, upstream decisions, auditing access, and opt-out or opt-in reliability. Specific resources such as computing power [16] are popularly tracked by annual reports on the field of AI [145, 27].
Mitigation and Intervention Policymakers can minimize resource gaps by making high-cost resources, such as computing power, accessible via applications and grants to researchers and low- resource organizations. Intercultural dialogues [48] that meaningfully address power imbalances and lowering the barrier for underrepresented peoples to contribute can improve harms from resource gaps. This can include accessible interfaces to interact with and conduct research on generative AI systems and low- to no-code tooling.
# 4.2.5.2 Environmental Impacts
In addition to the 4.1.6 Environmental Costs and Carbon Emissions from a system itself, evaluating impact on the Earth can follow popular frameworks and analyses.
|
2306.05949#63
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 63 |
[40] Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents. July 2022. doi: 10.48550/arXiv. 2207.01206.
[41] Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. CoRR, abs/2210.03629, 2022. doi: 10.48550/arXiv.2210.03629. URL https://doi.org/10.48550/arXiv.2210.03629.
[42] Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1321â1331, Beijing, China, 2015. Association for Computational Linguistics. doi: 10.3115/v1/P15-1128.
14
|
2306.06070#63
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 63 |
23
Large datasets of chemistry-related text are available from open-access platforms such as arXiv and PubChem. These articles contain titles, abstracts, and often complete manuscripts, which can be a testbed for evaluating LLMs as these titles and abstracts are usually written by expert researchers. Ideally, an LLM should be able to generate a title of an abstract close to the one developed by the expert, which can be considered a specialized text-summarization task. Similarly, given a title, an LLM should generate text close to the original abstract of the article, which can be considered a specialized text-generation task.
These tasks have been introduced by the AbstractToTitle & TitleToAbstract team (Kamal Choudhary) in the JARVIS-ChemNLP package [95]. For text summariza- tion, it uses a pre-trained Text-to-Text Transfer Transformer (T5) model developed by Google [96] that is further ï¬ne-tuned to produce summaries of abstracts. On the arXiv condensed-matter physics (cond-mat) data, the team found that ï¬ne-tuning the model can help improve the performance (Recall-Oriented Understudy for Gisting Evaluation (ROUGE)-1 score of 39.0 % which is better than an untrained model score of 30.8 % for an 80/20 split).
|
2306.06283#63
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 63 |
Double Q-Learning [van Hasselt, 2010] is usually leveraged to ameliorate over-estimation for lookup-based Q-Learning. Table 13 shows the Q value estimation results with Double Q-Learning applied. Over-estimation does be suppressed, however, serious under-estimation is introduced, and the estimation error fails to ameliorate. This is explained by that Double Q-Learning iteratively updates two Q value lookups and requires more steps to converge to an accurate enough estimation. In contrast, plain Q-Learning performs better in few-step circumstances.
Table 13: Comparison of the average reward estimation of the full model and the Double Q-Learning model
Task Set Setting #Epochs Avg Reward Estimation Avg Training Reward WebShop Full Model +DoubleQL +DoubleQL 3 3 6 0.86 0.71 0.69 0.84 0.75 0.77 0.02 0.04 0.08 2.38 5.33 10.39 WikiHow Full Model +DoubleQL +DoubleQL 3 3 6 2.48 2.47 2.70 2.60 2.90 2.90 0.12 0.43 0.20 4.62 14.83 6.90
# Abs Error Relative Error
16
ââ Webshop 2504 â+â WikiHow <= Webshop 200 150 #Experiences Experience Increments 100 50 Epochs Epochs
# (a) Number of experiences in each training epoch
|
2306.07929#63
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 64 |
answer is more comprehensive and useful for someone looking to understand Japanese business etiquette. GPT-4 Judgment (when B is placed in the first position): Both Assistant A and Assistant B provide helpful and relevant information about business etiquette norms in Japan. However, Assistant Bâs answer is more detailed and covers a wider range of topics, such as addressing people by their titles, avoiding direct eye contact, and being mindful of communication styles. Assistant Aâs answer is more concise but lacks some of the depth found in Assistant Bâs response. Therefore, Assistant Bâs answer is better in this case. / Figure 11: An example of position bias. When Assistant A is placed in the first position, GPT-4
|
2306.05685#64
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 64 |
[15] Paul Denny, Andrew Luxton-Reilly, and Ewan Tempero. 2012. All Syntax Errors Are Not Equal. In Proc. of the 17th ACM Annual Conf. on Innovation and Tech- nology in Computer Science Education (Haifa, Israel) (ITiCSE â12). ACM, NY, NY, USA, 75â80. https://doi.org/10.1145/2325296.2325318
[16] Paul Denny, James Prather, Brett A Becker, James Finnie-Ansley, Arto Hellas, Juho Leinonen, Andrew Luxton-Reilly, Brent N Reeves, Eddie Antonio Santos, and Sami Sarsa. 2023. Computing Education in the Era of Generative AI. arXiv preprint arXiv:2306.02608 (2023).
|
2306.05715#64
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 64 |
Ji, Y., Gong, Y., Deng, Y., Peng, Y., Niu, Q., Ma, B., and Li, X. (2023b). Towards better instruction following language models for chinese: Investigating the impact of training data and evaluation. arXiv preprint arXiv:2304.07854.
Kpf, A., Kilcher, Y., von Rütte, D., Anagnostidis, S., Tam, Z.-R., Stevens, K., Barhoum, A., Duc, N. M., Stanley, O., Nagyfi, R., ES, S., Suri, S., Glushkov, D., Dantuluri, A., Maguire, A., Schuhmann, C., Nguyen, H., and Mattick, A. (2023). Openassistant conversations â democratizing large language model alignment.
Liang, P., Bommasani, R., Lee, T., Tsipras, D., Soylu, D., Yasunaga, M., Zhang, Y., Narayanan, D., Wu, Y., Kumar, A., et al. (2022). Holistic evaluation of language models. arXiv preprint arXiv:2211.09110.
|
2306.05783#64
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 64 |
[Hua et al., 2023b] Wenyue Hua, Shuyuan Xu, Yingqiang How to index item ids Ge, and Yongfeng Zhang. for recommendation foundation models. arXiv preprint arXiv:2305.06569, 2023.
[Huang and Chang, 2022] Jie Huang and Kevin Chen-Chuan Chang. Towards reasoning in large language models: A survey. arXiv preprint arXiv:2212.10403, 2022.
[Jiao et al., 2019] Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. Tinybert: Distilling bert for natural language understand- ing. arXiv preprint arXiv:1909.10351, 2019.
[Kang et al., 2023] Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed Chi, and Derek Zhiyuan Cheng. Do llms understand user pref- erences? evaluating llms on user rating prediction. arXiv preprint arXiv:2305.06474, 2023.
|
2306.05817#64
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 64 |
In addition to the 4.1.6 Environmental Costs and Carbon Emissions from a system itself, evaluating impact on the Earth can follow popular frameworks and analyses.
What to Evaluate Environmental, social, and governance (ESG) frameworks and the Scope 1, 2, and 3 system can give structure to how developers track carbon emissions [195]. Scope 3 emissions, the indirect emissions often outside a developerâs control, should account for a generative AI systemâs lifecycle including in deployment [141]. Long-term effects of AI environmental impacts on the world and people can range from from inequity to quality of life [194]. Research to evaluate overall impacts of climate change is ongoing [3].
|
2306.05949#64
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 64 |
14
[43] Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir R. Radev. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In Ellen Riloff, David Chiang, Julia Hockenmaier, and Junâichi Tsujii, editors, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018, pages 3911â3921. Association for Computational Linguistics, 2018. doi: 10.18653/v1/d18-1425. URL https://doi.org/10.18653/v1/d18-1425.
|
2306.06070#64
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
2306.06283
| 64 |
For text generation, JARVIS-ChemNLP ï¬netunes the pretrained GPT-2-medium [48] model available in the HuggingFace library. [97] After ï¬netuning, the team found a ROUGE score of 31.7 %, which is a good starting point for pre-suggestion text applica- tions. Both tasks with well-deï¬ned train and test splits are now available in the JARVIS- Leaderboard platform for the AI community to compare other LLMs and systematically improve the performance.
In the future, such title to abstract capabilities can be extended to generating full- length drafts with appropriate tables, multi-modal ï¬gures, and results as an initial start for the human researcher to help in the technical writing processes. Note that there have been recent developments in providing guidelines for using LLM-generated text in technical manuscripts [98], so such an LLM model should be considered as an assistant of writing and not the master/author of the manuscripts.
# D. Education
Given all the opportunities LLM open for materials science and chemistry, there is an urgent need for education to adapt. Interestingly, LLMs also provide us with entirely
24
|
2306.06283#64
|
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
|
Large-language models (LLMs) such as GPT-4 caught the interest of many
scientists. Recent studies suggested that these models could be useful in
chemistry and materials science. To explore these possibilities, we organized a
hackathon.
This article chronicles the projects built as part of this hackathon.
Participants employed LLMs for various applications, including predicting
properties of molecules and materials, designing novel interfaces for tools,
extracting knowledge from unstructured data, and developing new educational
applications.
The diverse topics and the fact that working prototypes could be generated in
less than two days highlight that LLMs will profoundly impact the future of our
fields. The rich collection of ideas and projects also indicates that the
applications of LLMs are not limited to materials science and chemistry but
offer potential benefits to a wide range of scientific disciplines.
|
http://arxiv.org/pdf/2306.06283
|
Kevin Maik Jablonka, Qianxiang Ai, Alexander Al-Feghali, Shruti Badhwar, Joshua D. Bocarsly, Andres M Bran, Stefan Bringuier, L. Catherine Brinson, Kamal Choudhary, Defne Circi, Sam Cox, Wibe A. de Jong, Matthew L. Evans, Nicolas Gastellu, Jerome Genzling, María Victoria Gil, Ankur K. Gupta, Zhi Hong, Alishba Imran, Sabine Kruschwitz, Anne Labarre, Jakub Lála, Tao Liu, Steven Ma, Sauradeep Majumdar, Garrett W. Merz, Nicolas Moitessier, Elias Moubarak, Beatriz Mouriño, Brenden Pelkie, Michael Pieler, Mayk Caldas Ramos, Bojana Ranković, Samuel G. Rodriques, Jacob N. Sanders, Philippe Schwaller, Marcus Schwarting, Jiale Shi, Berend Smit, Ben E. Smith, Joren Van Herck, Christoph Völker, Logan Ward, Sean Warren, Benjamin Weiser, Sylvester Zhang, Xiaoqi Zhang, Ghezal Ahmad Zia, Aristana Scourtas, KJ Schmidt, Ian Foster, Andrew D. White, Ben Blaiszik
|
cond-mat.mtrl-sci, cs.LG, physics.chem-ph
| null | null |
cond-mat.mtrl-sci
|
20230609
|
20230714
|
[
{
"id": "2209.08203"
},
{
"id": "2212.04450"
}
] |
2306.07929
| 64 |
ââ Webshop 2504 â+â WikiHow <= Webshop 200 150 #Experiences Experience Increments 100 50 Epochs Epochs
# (a) Number of experiences in each training epoch
(b) Number of new experiences in each training epoch. The dashed lines are acquired by performing the least squares fit to the data points.
Figure 7: Variation of the experience number in the training process
As regards whether the LLM learns the certain Q value function, predicted values of LLM during the test phase on WebShop are inspected. The average absolute error is 0.417. This fact indicates that the LLM does not really learn the certain Q function, as the reward in WebShop is always between 0 and 1. Nevertheless, the LLM can still predict the appropriate actions. This is due to the inessentiality of absolutely precise Q value prediction during test. It is the relative relation between the values of candidate actions that is truly important. Once LLM can distinguish the valuable actions from candidates, it can take the right policy.
# F Example of the exemplars
An example of the input exemplar for WebShop and WikiHow is given in Figure 8 and Figure 9, respectively.
# G Case study
Figure 10 gives a case from the ablation study on necessity of the discouraged actions. If the discouraged actions are omitted in the action advice from an experience without encouraged actions, the LLM will have no ability to avoid failures of the same pattern.
|
2306.07929#64
|
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
|
Inspired by the insights in cognitive science with respect to human memory
and reasoning mechanism, a novel evolvable LLM-based (Large Language Model)
agent framework is proposed as REMEMBERER. By equipping the LLM with a
long-term experience memory, REMEMBERER is capable of exploiting the
experiences from the past episodes even for different task goals, which excels
an LLM-based agent with fixed exemplars or equipped with a transient working
memory. We further introduce Reinforcement Learning with Experience Memory
(RLEM) to update the memory. Thus, the whole system can learn from the
experiences of both success and failure, and evolve its capability without
fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER
constitutes a semi-parametric RL agent. Extensive experiments are conducted on
two RL task sets to evaluate the proposed framework. The average results with
different initialization and training sets exceed the prior SOTA by 4% and 2%
for the success rate on two task sets and demonstrate the superiority and
robustness of REMEMBERER.
|
http://arxiv.org/pdf/2306.07929
|
Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu
|
cs.CL, cs.AI
| null | null |
cs.CL
|
20230609
|
20231030
|
[
{
"id": "2201.06009"
}
] |
2306.05685
| 65 |
Figure 11: An example of position bias. When Assistant A is placed in the first position, GPT-4 thinks A is better, but its verdict changes when we swap the position of A and B. We observe similar pattern from other LLM judges such as Claude/GPT-3.5.
18
Question: What is the central dogma of molecular biology? What processes are involved? Who named this?
# Assistant A:
# Assistant B:
The central dogma of molecular biology is the fundamental principle that explains how genetic information flows within a biological system. It states that DNA is transcribed into RNA, which is then translated into proteins. This means that the genetic information stored in DNA is first copied into RNA, which then serves as a template for the synthesis of proteins.
The central dogma of molecular biology is the fundamental principle that explains how genetic information flows within a biological system. It states that DNA is transcribed into RNA, which is then translated into proteins. This means that the genetic information stored in DNA is first copied into RNA, which then serves as a template for the synthesis of proteins.
The processes involved in the central dogma are:
The processes involved in the central dogma are:
|
2306.05685#65
|
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
|
Evaluating large language model (LLM) based chat assistants is challenging
due to their broad capabilities and the inadequacy of existing benchmarks in
measuring human preferences. To address this, we explore using strong LLMs as
judges to evaluate these models on more open-ended questions. We examine the
usage and limitations of LLM-as-a-judge, including position, verbosity, and
self-enhancement biases, as well as limited reasoning ability, and propose
solutions to mitigate some of them. We then verify the agreement between LLM
judges and human preferences by introducing two benchmarks: MT-bench, a
multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our
results reveal that strong LLM judges like GPT-4 can match both controlled and
crowdsourced human preferences well, achieving over 80% agreement, the same
level of agreement between humans. Hence, LLM-as-a-judge is a scalable and
explainable way to approximate human preferences, which are otherwise very
expensive to obtain. Additionally, we show our benchmark and traditional
benchmarks complement each other by evaluating several variants of LLaMA and
Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with
human preferences are publicly available at
https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
|
http://arxiv.org/pdf/2306.05685
|
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica
|
cs.CL, cs.AI
|
NeurIPS 2023 Datasets and Benchmarks Track
| null |
cs.CL
|
20230609
|
20231224
|
[
{
"id": "2302.13971"
},
{
"id": "1905.07830"
},
{
"id": "1803.05457"
},
{
"id": "2305.10403"
},
{
"id": "2304.07327"
},
{
"id": "2201.11903"
},
{
"id": "2009.03300"
},
{
"id": "2304.12244"
},
{
"id": "2306.12420"
},
{
"id": "2304.06364"
},
{
"id": "2107.03374"
},
{
"id": "2306.04751"
},
{
"id": "2211.09110"
},
{
"id": "2301.13688"
},
{
"id": "2004.14602"
},
{
"id": "2110.14168"
},
{
"id": "2305.15717"
},
{
"id": "2211.05719"
},
{
"id": "2206.04615"
},
{
"id": "2204.05862"
},
{
"id": "2305.01937"
},
{
"id": "2305.14387"
},
{
"id": "2305.17926"
},
{
"id": "2304.03277"
},
{
"id": "2303.12712"
},
{
"id": "2305.14314"
},
{
"id": "2303.15056"
},
{
"id": "2109.01652"
},
{
"id": "2305.11206"
},
{
"id": "2109.07958"
},
{
"id": "2302.07736"
}
] |
2306.05715
| 65 |
[17] Paul Denny, James Prather, Brett A. Becker, Catherine Mooney, John Homer, Zachary C Albrecht, and Garrett B. Powell. 2021. On Designing Programming Error Messages for Novices: Readability and Its Constituent Factors. In Proc. of the 2021 CHI Conf. on Human Factors in Computing Systems (Yokohama, Japan) (CHI â21). Association for Computing Machinery, New York, NY,USA, Article 55, 15 pages. https://doi.org/10.1145/3411764.3445696
[18] Paul Denny, Sami Sarsa, Arto Hellas, and Juho Leinonen. 2022. Robosourcing Educational ResourcesâLeveraging Large Language Models for Learnersourcing. arXiv preprint arXiv:2211.04715 (2022).
[19] Christopher Douce, David Livingstone, and James Orwell. 2005. Automatic test- based assessment of programming: A review. J. on Educational Resources in Com- puting (JERIC) 5, 3 (2005), 4.
[20] Thomas Dy and Ma Mercedes Rodrigo. 2010. A detector for non-literal Java errors. In Proc. of the 10th Koli Calling Int. Conf. on Computing Education Research. ACM, 118â122.
|
2306.05715#65
|
Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
|
Background and Context: Over the past year, large language models (LLMs) have
taken the world by storm. In computing education, like in other walks of life,
many opportunities and threats have emerged as a consequence.
Objectives: In this article, we explore such opportunities and threats in a
specific area: responding to student programmers' help requests. More
specifically, we assess how good LLMs are at identifying issues in problematic
code that students request help on.
Method: We collected a sample of help requests and code from an online
programming course. We then prompted two different LLMs (OpenAI Codex and
GPT-3.5) to identify and explain the issues in the students' code and assessed
the LLM-generated answers both quantitatively and qualitatively.
Findings: GPT-3.5 outperforms Codex in most respects. Both LLMs frequently
find at least one actual issue in each student program (GPT-3.5 in 90% of the
cases). Neither LLM excels at finding all the issues (GPT-3.5 finding them 57%
of the time). False positives are common (40% chance for GPT-3.5). The advice
that the LLMs provide on the issues is often sensible. The LLMs perform better
on issues involving program logic rather than on output formatting. Model
solutions are frequently provided even when the LLM is prompted not to. LLM
responses to prompts in a non-English language are only slightly worse than
responses to English prompts.
Implications: Our results continue to highlight the utility of LLMs in
programming education. At the same time, the results highlight the
unreliability of LLMs: LLMs make some of the same mistakes that students do,
perhaps especially when formatting output as required by automated assessment
systems. Our study informs teachers interested in using LLMs as well as future
efforts to customize LLMs for the needs of programming education.
|
http://arxiv.org/pdf/2306.05715
|
Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva
|
cs.CY, cs.AI, cs.CL, cs.HC, cs.SE
|
13 pages, 1 figure. To be published in Proceedings of the 2023 ACM
Conference on International Computing Education Research V.1 (ICER '23 V1)
| null |
cs.CY
|
20230609
|
20230609
|
[
{
"id": "2004.09456"
},
{
"id": "2302.07427"
},
{
"id": "2203.02155"
},
{
"id": "2304.02491"
},
{
"id": "2211.04715"
},
{
"id": "2306.02608"
},
{
"id": "2303.08774"
},
{
"id": "2304.03938"
}
] |
2306.05783
| 65 |
Liu, C., Jin, R., Ren, Y., Yu, L., Dong, T., Peng, X., Zhang, S., Peng, J., Zhang, P., Lyu, Q., et al. (2023). M3ke: A massive multi-level multi-subject knowledge evaluation benchmark for chinese large language models. arXiv preprint arXiv:2305.10263.
Muennighoff, N., Wang, T., Sutawika, L., Roberts, A., Biderman, S., Scao, T. L., Bari, M. S., Shen, S., Yong, Z.-X., Schoelkopf, H., Tang, X., Radev, D., Aji, A. F., Almubarak, K., Albanie, S., Alyafeai, Z., Webson, A., Raff, E., and Raffel, C. (2022). Crosslingual generalization through multitask finetuning.
Niklaus, J., Matoshi, V., Rani, P., Galassi, A., Stürmer, M., and Chalkidis, I. (2023). Lextreme: A multi-lingual and multi-task benchmark for the legal domain. arXiv preprint arXiv:2301.13126.
|
2306.05783#65
|
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
|
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align
with the rapid development of large language models (LLMs). We present Xiezhi,
the most comprehensive evaluation suite designed to assess holistic domain
knowledge. Xiezhi comprises multiple-choice questions across 516 diverse
disciplines ranging from 13 different subjects with 249,587 questions and
accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k
questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results
indicate that LLMs exceed average performance of humans in science,
engineering, agronomy, medicine, and art, but fall short in economics,
jurisprudence, pedagogy, literature, history, and management. We anticipate
Xiezhi will help analyze important strengths and shortcomings of LLMs, and the
benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.
|
http://arxiv.org/pdf/2306.05783
|
Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
|
cs.CL
|
Under review of NeurIPS 2023
| null |
cs.CL
|
20230609
|
20230615
|
[
{
"id": "2301.13126"
},
{
"id": "2302.13971"
},
{
"id": "2303.04048"
},
{
"id": "1905.07830"
},
{
"id": "2304.12986"
},
{
"id": "2304.07854"
},
{
"id": "2211.05100"
},
{
"id": "1909.00277"
},
{
"id": "2305.10263"
},
{
"id": "1909.06058"
},
{
"id": "2206.07682"
},
{
"id": "2304.06364"
},
{
"id": "2211.09110"
},
{
"id": "2305.08322"
},
{
"id": "2210.11416"
},
{
"id": "2212.08073"
},
{
"id": "2210.09261"
},
{
"id": "2206.04615"
},
{
"id": "2303.18223"
},
{
"id": "2302.09419"
},
{
"id": "2303.14742"
},
{
"id": "2111.10952"
},
{
"id": "2301.12726"
},
{
"id": "2304.01933"
},
{
"id": "2106.09685"
},
{
"id": "2303.12712"
},
{
"id": "2212.09251"
},
{
"id": "2304.01196"
},
{
"id": "2105.09938"
}
] |
2306.05817
| 65 |
[Li et al., 2023a] Chen Li, Yixiao Ge, Jiayong Mao, Dian Taggpt: Large language mod- arXiv preprint Li, and Ying Shan. els are zero-shot multimodal taggers. arXiv:2304.03022, 2023.
[Li et al., 2023b] Jiacheng Li, Ming Wang, Jin Li, Jin- miao Fu, Xin Shen, Jingbo Shang, and Julian McAuley. is all you need: Learning language representa- Text arXiv preprint tions for sequential recommendation. arXiv:2305.13731, 2023.
[Li et al., 2023c] Jinming Li, Wentao Zhang, Tian Wang, Guanglei Xiong, Alan Lu, and Gerard Medioni. Gpt4rec: A generative framework for personalized recommenda- arXiv preprint tion and user interests interpretation. arXiv:2304.03879, 2023.
[Li et al., 2023d] Ruyu Li, Wenhao Deng, Yu Cheng, Zheng Yuan, Jiaqi Zhang, and Fajie Yuan. Exploring the upper limits of text-based collaborative ï¬ltering using large lan- guage models: Discoveries and insights. arXiv preprint arXiv:2305.11700, 2023.
|
2306.05817#65
|
How Can Recommender Systems Benefit from Large Language Models: A Survey
|
Recommender systems (RS) play important roles to match users' information
needs for Internet applications. In natural language processing (NLP) domains,
large language model (LLM) has shown astonishing emergent abilities (e.g.,
instruction following, reasoning), thus giving rise to the promising research
direction of adapting LLM to RS for performance enhancements and user
experience improvements. In this paper, we conduct a comprehensive survey on
this research direction from an application-oriented view. We first summarize
existing research works from two orthogonal perspectives: where and how to
adapt LLM to RS. For the "WHERE" question, we discuss the roles that LLM could
play in different stages of the recommendation pipeline, i.e., feature
engineering, feature encoder, scoring/ranking function, and pipeline
controller. For the "HOW" question, we investigate the training and inference
strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to
tune LLMs or not, and whether to involve conventional recommendation model
(CRM) for inference. Detailed analysis and general development trajectories are
provided for both questions, respectively. Then, we highlight key challenges in
adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and
ethics. Finally, we summarize the survey and discuss the future prospects. We
also actively maintain a GitHub repository for papers and other related
resources in this rising direction:
https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.
|
http://arxiv.org/pdf/2306.05817
|
Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
|
cs.IR, cs.AI
|
15 pages; 3 figures; summarization table in appendix
| null |
cs.IR
|
20230609
|
20230628
|
[
{
"id": "2302.13971"
},
{
"id": "1810.04805"
},
{
"id": "2304.05263"
},
{
"id": "2305.07001"
},
{
"id": "2305.11700"
},
{
"id": "2305.06566"
},
{
"id": "2305.15756"
},
{
"id": "2105.08318"
},
{
"id": "2304.03879"
},
{
"id": "2303.08559"
},
{
"id": "1703.04247"
},
{
"id": "2206.07682"
},
{
"id": "2305.07961"
},
{
"id": "2305.05973"
},
{
"id": "2305.15498"
},
{
"id": "2306.11114"
},
{
"id": "2305.04518"
},
{
"id": "2305.00447"
},
{
"id": "2305.02182"
},
{
"id": "2305.08845"
},
{
"id": "2305.12090"
},
{
"id": "2212.10403"
},
{
"id": "2304.03022"
},
{
"id": "2305.07609"
},
{
"id": "2209.08060"
},
{
"id": "2209.07562"
},
{
"id": "2304.09542"
},
{
"id": "2303.14524"
},
{
"id": "2305.15673"
},
{
"id": "2303.18223"
},
{
"id": "2304.10149"
},
{
"id": "1908.08167"
},
{
"id": "1909.10351"
},
{
"id": "2305.15036"
},
{
"id": "2305.12081"
},
{
"id": "2304.07862"
},
{
"id": "2305.03017"
},
{
"id": "2305.09858"
},
{
"id": "2305.06474"
},
{
"id": "2305.13731"
},
{
"id": "2304.03153"
},
{
"id": "2205.08084"
},
{
"id": "2106.09685"
},
{
"id": "2306.10702"
},
{
"id": "2306.02250"
},
{
"id": "2303.13835"
},
{
"id": "2305.14302"
},
{
"id": "2302.03735"
},
{
"id": "2306.02841"
},
{
"id": "2305.11206"
},
{
"id": "2203.15876"
},
{
"id": "2305.07622"
},
{
"id": "2306.10933"
},
{
"id": "2305.06569"
},
{
"id": "2206.06190"
}
] |
2306.05949
| 65 |
Given the intensive use of energy and compute required to develop generative AI systems, due dili- gence is required regarding sustainability claims. Company practices of offsetting carbon footprints include purchasing renewable energy certificates (RECs), e.g. tokens representing a utilityâs green energy generation. However REC purchases may offset carbon emissions to achieve ânet zeroâ on paper, while in reality still using fossil fuel based energy to run systems. This is due to the purchased renewable energy being generated at another time and location than the energy used by the company. Tracking the validity of high energy users claims that their theoretical carbon usage matches their actual use of carbon intensive energy can be carried out using time stamped certificates. Further transparency around industry figures on energy consumption will be required to adequately intervene [115].
Mitigation and Interventions Systemic change is a prerequisite to energy and carbon efficiency in AI systems, from energy efficient default settings for platforms and tools, and an awareness of balancing gains with cost, for example, weighing energy costs, both social and monetary, with the performance gains of a new model before deploying it. Best practices for developers and researchers include choosing efficient testing environments, promoting reproducibility, and standardized reporting. An energy efficiency leaderboard can incentivise responsible research [105].
|
2306.05949#65
|
Evaluating the Social Impact of Generative AI Systems in Systems and Society
|
Generative AI systems across modalities, ranging from text, image, audio, and
video, have broad social impacts, but there exists no official standard for
means of evaluating those impacts and which impacts should be evaluated. We
move toward a standard approach in evaluating a generative AI system for any
modality, in two overarching categories: what is able to be evaluated in a base
system that has no predetermined application and what is able to be evaluated
in society. We describe specific social impact categories and how to approach
and conduct evaluations in the base technical system, then in people and
society. Our framework for a base system defines seven categories of social
impact: bias, stereotypes, and representational harms; cultural values and
sensitive content; disparate performance; privacy and data protection;
financial costs; environmental costs; and data and content moderation labor
costs. Suggested methods for evaluation apply to all modalities and analyses of
the limitations of existing evaluations serve as a starting point for necessary
investment in future evaluations. We offer five overarching categories for what
is able to be evaluated in society, each with their own subcategories:
trustworthiness and autonomy; inequality, marginalization, and violence;
concentration of authority; labor and creativity; and ecosystem and
environment. Each subcategory includes recommendations for mitigating harm. We
are concurrently crafting an evaluation repository for the AI research
community to contribute existing evaluations along the given categories. This
version will be updated following a CRAFT session at ACM FAccT 2023.
|
http://arxiv.org/pdf/2306.05949
|
Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev
|
cs.CY, cs.AI
| null | null |
cs.CY
|
20230609
|
20230612
|
[
{
"id": "2007.04068"
},
{
"id": "2305.09800"
},
{
"id": "1908.09203"
},
{
"id": "2202.05520"
},
{
"id": "2302.10329"
},
{
"id": "2107.03374"
},
{
"id": "2210.06245"
},
{
"id": "2211.02001"
},
{
"id": "2212.08073"
},
{
"id": "2303.08774"
},
{
"id": "2301.10226"
},
{
"id": "2202.02647"
},
{
"id": "2112.10752"
},
{
"id": "2206.04615"
},
{
"id": "2202.00885"
},
{
"id": "2010.15581"
},
{
"id": "2305.09941"
},
{
"id": "2301.04246"
},
{
"id": "2304.12298"
},
{
"id": "2203.09509"
},
{
"id": "2207.14157"
},
{
"id": "2102.09692"
},
{
"id": "1804.10999"
},
{
"id": "2303.11156"
},
{
"id": "2104.06390"
},
{
"id": "2002.05651"
}
] |
2306.06070
| 65 |
[44] Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. A survey of large language models. CoRR, abs/2303.18223, 2023. doi: 10.48550/ARXIV.2303.18223. URL https://doi.org/10.48550/arXiv.2303.18223.
|
2306.06070#65
|
Mind2Web: Towards a Generalist Agent for the Web
|
We introduce Mind2Web, the first dataset for developing and evaluating
generalist agents for the web that can follow language instructions to complete
complex tasks on any website. Existing datasets for web agents either use
simulated websites or only cover a limited set of websites and tasks, thus not
suitable for generalist web agents. With over 2,000 open-ended tasks collected
from 137 websites spanning 31 domains and crowdsourced action sequences for the
tasks, Mind2Web provides three necessary ingredients for building generalist
web agents: 1) diverse domains, websites, and tasks, 2) use of real-world
websites instead of simulated and simplified ones, and 3) a broad spectrum of
user interaction patterns. Based on Mind2Web, we conduct an initial exploration
of using large language models (LLMs) for building generalist web agents. While
the raw HTML of real-world websites are often too large to be fed to LLMs, we
show that first filtering it with a small LM significantly improves the
effectiveness and efficiency of LLMs. Our solution demonstrates a decent level
of performance, even on websites or entire domains the model has never seen
before, but there is still a substantial room to improve towards truly
generalizable agents. We open-source our dataset, model implementation, and
trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further
research on building a generalist agent for the web.
|
http://arxiv.org/pdf/2306.06070
|
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su
|
cs.CL
|
Website: https://osu-nlp-group.github.io/Mind2Web. Updated with
supplementary material. NeurIPS'23 Spotlight
| null |
cs.CL
|
20230609
|
20231209
|
[] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.