id
stringlengths 12
15
| title
stringlengths 8
162
| content
stringlengths 1
17.6k
| prechunk_id
stringlengths 0
15
| postchunk_id
stringlengths 0
15
| arxiv_id
stringlengths 10
10
| references
sequencelengths 1
1
|
|---|---|---|---|---|---|---|
2309.16797#28 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Did aristotle use a laptop? A question answering benchmark with implicit reasoning strategies. Trans. Assoc. Comput. Linguistics, 9:346â 361, 2021. doi: 10.1162/tacl\ a\ 00370. URL https://doi. org/10.1162/tacl_a_00370. Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, and Yujiu Yang. Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers, September 2023. | 2309.16797#27 | 2309.16797#29 | 2309.16797 | [
"2305.03495"
] |
2309.16797#29 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Inman Harvey. The microbial genetic algorithm. In Advances in Artificial Life. Darwin Meets von Neumann: 10th European Conference, ECAL 2009, Budapest, Hungary, September 13-16, 2009, Revised Selected Papers, Part II 10, pp. 126â 133. Springer, 2011. Mark Hauschild and Martin Pelikan. An introduction and survey of estimation of distribution algo- rithms. Swarm and evolutionary computation, 1(3):111â 128, 2011. Or Honovich, Uri Shaham, Samuel R. Bowman, and Omer Levy. | 2309.16797#28 | 2309.16797#30 | 2309.16797 | [
"2305.03495"
] |
2309.16797#30 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Instruction induction: From few examples to natural language task descriptions. In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 1935â 1952. Association for Computational Linguistics, 2023. doi: 10.18653/v1/2023.acl-long. 108. URL https://doi.org/10.18653/v1/2023.acl-long.108. Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. | 2309.16797#29 | 2309.16797#31 | 2309.16797 | [
"2305.03495"
] |
2309.16797#31 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Learning to solve arithmetic word problems with verb categorization. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 523â 533, Doha, Qatar, October 2014. Association for Computational Linguistics. doi: 10.3115/v1/D14-1058. URL https://aclanthology.org/D14-1058. Cheng-Yu Hsieh, Chun-Liang Li, Chih-Kuan Yeh, Hootan Nakhost, Yasuhisa Fujii, Alex Ratner, Ranjay Krishna, Chen-Yu Lee, and Tomas Pfister. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. In Anna Rogers, Jordan L. Boyd- Graber, and Naoaki Okazaki (eds.), Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 8003â 8017. Association for Computational Linguistics, 2023. doi: 10.18653/v1/2023.findings-acl.507. URL https://doi.org/10. 18653/v1/2023.findings-acl.507. Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. Large language models can self-improve. CoRR, abs/2210.11610, 2022. doi: 10.48550/ arXiv.2210.11610. URL https://doi.org/10.48550/arXiv.2210.11610. Kazuki Irie, Imanol Schlag, R´obert Csord´as, and J¨urgen Schmidhuber. A modern self-referential weight matrix that learns to modify itself. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv´ari, Gang Niu, and Sivan Sabato (eds.), International Conference on Machine | 2309.16797#30 | 2309.16797#32 | 2309.16797 | [
"2305.03495"
] |
2309.16797#32 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 11 Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Pro- ceedings of Machine Learning Research, pp. 9660â 9677. PMLR, 2022. URL https:// proceedings.mlr.press/v162/irie22b.html. Max Jaderberg, Valentin Dalibard, Simon Osindero, Wojciech M. Czarnecki, Jeff Donahue, Ali Razavi, Oriol Vinyals, Tim Green, Iain Dunning, Karen Simonyan, Chrisantha Fernando, and Koray Kavukcuoglu. Population based training of neural networks. CoRR, abs/1711.09846, 2017a. URL http://arxiv.org/abs/1711.09846. Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z. Leibo, David Silver, and Koray Kavukcuoglu. Reinforcement learning with unsupervised auxiliary tasks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net, 2017b. URL https://openreview. net/forum?id=SJ6yPD5xg. Minqi Jiang, Michael Dennis, Jack Parker-Holder, Jakob N. Foerster, Edward Grefenstette, and Tim Rockt¨aschel. Replay-guided adversarial environment design. | 2309.16797#31 | 2309.16797#33 | 2309.16797 | [
"2305.03495"
] |
2309.16797#33 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | In Marcâ Aurelio Ran- zato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (eds.), Advances in Neural Information Processing Systems 34: Annual Conference on Neu- ral Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 1884â 1897, 2021a. URL https://proceedings.neurips.cc/paper/2021/hash/ 0e915db6326b6fb6a3c56546980a8c93-Abstract.html. Minqi Jiang, Edward Grefenstette, and Tim Rockt¨aschel. Prioritized level replay. In Marina Meila and Tong Zhang (eds.), Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, volume 139 of Proceedings of Machine Learning Re- search, pp. 4940â 4950. PMLR, 2021b. URL http://proceedings.mlr.press/v139/ jiang21b.html. Minqi Jiang, Tim Rockt¨aschel, and Edward Grefenstette. General intelligence requires rethinking exploration. CoRR, abs/2211.07819, 2022. doi: 10.48550/arXiv.2211.07819. URL https: //doi.org/10.48550/arXiv.2211.07819. Louis Kirsch and J¨urgen Schmidhuber. Eliminating meta optimization through self-referential meta learning. CoRR, abs/2212.14392, 2022. doi: 10.48550/arXiv.2212.14392. URL https:// doi.org/10.48550/arXiv.2212.14392. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke In NeurIPS, 2022. http://papers.nips.cc/paper_files/paper/2022/hash/ Iwasawa. URL 8bb0d291acd4acf06ef112099c16f326-Abstract-Conference.html. Large language models are zero-shot reasoners. | 2309.16797#32 | 2309.16797#34 | 2309.16797 | [
"2305.03495"
] |
2309.16797#34 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, and Siena Du- mas Ang. Parsing algebraic word problems into equations. Transactions of the Association for Computational Linguistics, 3:585â 597, 2015. doi: 10.1162/tacl a 00160. URL https: //aclanthology.org/Q15-1042. Joel Lehman and Kenneth O. Stanley. | 2309.16797#33 | 2309.16797#35 | 2309.16797 | [
"2305.03495"
] |
2309.16797#35 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Evolving a diversity of virtual creatures through novelty In Natalio Krasnogor and Pier Luca Lanzi (eds.), 13th Annual search and local competition. Genetic and Evolutionary Computation Conference, GECCO 2011, Proceedings, Dublin, Ireland, July 12-16, 2011, pp. 211â 218. ACM, 2011a. doi: 10.1145/2001576.2001606. URL https: //doi.org/10.1145/2001576.2001606. Joel Lehman and Kenneth O. Stanley. Abandoning Objectives: Evolution Through the Search for Novelty Alone. Evolutionary Computation, 19(2):189â 223, June 2011b. ISSN 1063-6560. doi: 10.1162/EVCO a 00025. Joel Lehman, Jonathan Gordon, Shawn Jain, Kamal Ndousse, Cathy Yeh, and Kenneth O. Stanley. | 2309.16797#34 | 2309.16797#36 | 2309.16797 | [
"2305.03495"
] |
2309.16797#36 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Evolution through large models. CoRR, abs/2206.08896, 2022. doi: 10.48550/arXiv.2206.08896. URL https://doi.org/10.48550/arXiv.2206.08896. 12 Brian Lester, Rami Al-Rfou, and Noah Constant. The power of scale for parameter-efficient prompt tuning. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih (eds.), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pp. 3045â 3059. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021.emnlp-main.243. URL https://doi.org/10.18653/v1/2021.emnlp-main.243. | 2309.16797#35 | 2309.16797#37 | 2309.16797 | [
"2305.03495"
] |
2309.16797#37 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. Program induction by rationale gen- In Proceedings of the 55th eration: Learning to solve and explain algebraic word problems. Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 158â 167, Vancouver, Canada, July 2017. Association for Computational Linguistics. doi: 10.18653/v1/P17-1015. URL https://aclanthology.org/P17-1015. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. Lost in the middle: How language models use long contexts. CoRR, abs/2307.03172, 2023. doi: 10.48550/arXiv.2307.03172. URL https://doi.org/10.48550/arXiv. 2307.03172. Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. GPT understands, too. CoRR, abs/2103.10385, 2021. URL https://arxiv.org/abs/2103. 10385. | 2309.16797#36 | 2309.16797#38 | 2309.16797 | [
"2305.03495"
] |
2309.16797#38 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, and Pontus Stenetorp. Fantastically In ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. Smaranda Muresan, Preslav Nakov, and Aline Villavicencio (eds.), Proceedings of the 60th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pp. 8086â 8098. Association for Computational Linguis- tics, 2022. doi: 10.18653/v1/2022.acl-long.556. URL https://doi.org/10.18653/v1/ 2022.acl-long.556. | 2309.16797#37 | 2309.16797#39 | 2309.16797 | [
"2305.03495"
] |
2309.16797#39 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Aman Madaan and Amir Yazdanbakhsh. Text and patterns: For effective chain of thought, it takes two to tango. CoRR, abs/2209.07686, 2022. doi: 10.48550/arXiv.2209.07686. URL https: //doi.org/10.48550/arXiv.2209.07686. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Sean Welleck, Bodhisattwa Prasad Ma- jumder, Shashank Gupta, Amir Yazdanbakhsh, and Peter Clark. Self-refine: Iterative refine- ment with self-feedback. CoRR, abs/2303.17651, 2023. doi: 10.48550/arXiv.2303.17651. URL https://doi.org/10.48550/arXiv.2303.17651. Elliot Meyerson, Mark J. Nelson, Herbie Bradley, Arash Moradi, Amy K. Hoover, and Joel Lehman. | 2309.16797#38 | 2309.16797#40 | 2309.16797 | [
"2305.03495"
] |
2309.16797#40 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Language model crossover: Variation through few-shot prompting. CoRR, abs/2302.12170, 2023. doi: 10.48550/arXiv.2302.12170. URL https://doi.org/10.48550/arXiv.2302. 12170. Suvir Mirchandani, Fei Xia, Pete Florence, Brian Ichter, Danny Driess, Montserrat Gonzalez Arenas, Kanishka Rao, Dorsa Sadigh, and Andy Zeng. Large language models as general pattern machines. CoRR, abs/2307.04721, 2023. doi: 10.48550/arXiv.2307.04721. URL https://doi.org/10.48550/arXiv.2307.04721. | 2309.16797#39 | 2309.16797#41 | 2309.16797 | [
"2305.03495"
] |
2309.16797#41 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Ioannis Mollas, Zoe Chrysopoulou, Stamatis Karlos, and Grigorios Tsoumakas. ETHOS: a multi-label hate speech detection dataset. Complex and Intelligent Systems, 8(6):4663â 4678, doi: 10.1007/s40747-021-00608-2. URL https://doi.org/10.1007% jan 2022. 2Fs40747-021-00608-2. Milad Moradi and Matthias Samwald. Evaluating the robustness of neural language models to input perturbations. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen- tau Yih (eds.), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pp. 1558â 1570. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021. emnlp-main.117. URL https://doi.org/10.18653/v1/2021.emnlp-main.117. | 2309.16797#40 | 2309.16797#42 | 2309.16797 | [
"2305.03495"
] |
2309.16797#42 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 13 Jean-Baptiste Mouret and Jeff Clune. Illuminating search spaces by mapping elites. CoRR, abs/1504.04909, 2015. URL http://arxiv.org/abs/1504.04909. Maxwell I. Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, Charles Sutton, and Au- gustus Odena. Show your work: Scratchpads for intermediate computation with language models. CoRR, abs/2112.00114, 2021. URL https://arxiv.org/abs/2112.00114. | 2309.16797#41 | 2309.16797#43 | 2309.16797 | [
"2305.03495"
] |
2309.16797#43 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Michael ¨Ollinger and G¨unther Knoblich. Psychological research on insight problem solving. In Recasting reality: Wolfgang Pauliâ s philosophical ideas and contemporary science, pp. 275â 300. Springer, 2009. Joon Sung Park, Joseph C. Oâ Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. Generative agents: Interactive simulacra of human behavior. CoRR, abs/2304.03442, 2023. doi: 10.48550/arXiv.2304.03442. URL https://doi.org/10. 48550/arXiv.2304.03442. Jack Parker-Holder, Minqi Jiang, Michael Dennis, Mikayel Samvelyan, Jakob N. Foerster, Ed- ward Grefenstette, and Tim Rockt¨aschel. Evolving curricula with regret-based environment In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv´ari, Gang Niu, design. and Sivan Sabato (eds.), International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Re- search, pp. 17473â 17498. PMLR, 2022. URL https://proceedings.mlr.press/ v162/parker-holder22a.html. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. Are NLP models really able to solve sim- ple math word problems? In Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-T¨ur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou (eds.), Proceedings of the 2021 Conference of the North American Chapter of the As- sociation for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021, pp. 2080â 2094. | 2309.16797#42 | 2309.16797#44 | 2309.16797 | [
"2305.03495"
] |
2309.16797#44 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021.naacl-main.168. URL https://doi.org/10.18653/v1/2021. naacl-main.168. Joshua L. Payne and Andreas Wagner. The causes of evolvability and their evolution. Nature Re- views Genetics, 20(1):24â 38, January 2019. ISSN 1471-0064. doi: 10.1038/s41576-018-0069-z. Massimo Pigliucci. | 2309.16797#43 | 2309.16797#45 | 2309.16797 | [
"2305.03495"
] |
2309.16797#45 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Is evolvability evolvable? Nature Reviews Genetics, 9(1):75â 82, January 2008. ISSN 1471-0064. doi: 10.1038/nrg2278. Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, and Michael Zeng. Automatic prompt optimization withâ gradient descentâ and beam search. arXiv preprint arXiv:2305.03495, 2023. Guanghui Qin and Jason Eisner. | 2309.16797#44 | 2309.16797#46 | 2309.16797 | [
"2305.03495"
] |
2309.16797#46 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Learning How to Ask: Querying LMs with Mixtures of Soft Prompts, April 2021. Subhro Roy and Dan Roth. arXiv:1608.01413, 2016. Solving general arithmetic word problems. arXiv preprint Timo Schick, Jane Dwivedi-Yu, Roberto Dess`ı, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. | 2309.16797#45 | 2309.16797#47 | 2309.16797 | [
"2305.03495"
] |
2309.16797#47 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Toolformer: Language Models Can Teach Themselves to Use Tools, February 2023. J. Schmidhuber. A â Self-Referentialâ Weight Matrix. ICANN â 93, pp. 446â 450, London, 1993. Springer. 978-1-4471-2063-6 107. In Stan Gielen and Bert Kappen (eds.), ISBN 978-1-4471-2063-6. doi: 10.1007/ J¨urgen Schmidhuber. Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments. 1990. | 2309.16797#46 | 2309.16797#48 | 2309.16797 | [
"2305.03495"
] |
2309.16797#48 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | J¨urgen Schmidhuber. Learning to Control Fast-Weight Memories: An Alternative to Dynamic Re- ISSN 0899-7667. doi: current Networks. Neural Computation, 4(1):131â 139, January 1992. 10.1162/neco.1992.4.1.131. 14 J¨urgen Schmidhuber. G¨odel machines: self-referential universal problem solvers making provably optimal self-improvements. arXiv preprint cs/0309048, 2003. Jimmy Secretan, Nicholas Beato, David B. D Ambrosio, Adelein Rodriguez, Adam Campbell, and Kenneth O. Stanley. | 2309.16797#47 | 2309.16797#49 | 2309.16797 | [
"2305.03495"
] |
2309.16797#49 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Picbreeder: Evolving pictures collaboratively online. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI â 08, pp. 1759â 1768, New York, NY, USA, April 2008. Association for Computing Machinery. ISBN 978-1-60558-011-1. doi: 10.1145/1357054.1357328. Ofer M Shir and Thomas B¨ack. Niching in evolution strategies. In Proceedings of the 7th annual conference on Genetic and evolutionary computation, pp. 915â 916, 2005. Kashun Shum, Shizhe Diao, and Tong Zhang. | 2309.16797#48 | 2309.16797#50 | 2309.16797 | [
"2305.03495"
] |
2309.16797#50 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Automatic prompt augmentation and selection with chain-of-thought from labeled data. CoRR, abs/2302.12822, 2023. doi: 10.48550/arXiv.2302. 12822. URL https://doi.org/10.48550/arXiv.2302.12822. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. CommonsenseQA: A ques- tion answering challenge targeting commonsense knowledge. In Proceedings of the 2019 Con- ference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4149â 4158, Minneapolis, Min- nesota, June 2019. Association for Computational Linguistics. doi: 10.18653/v1/N19-1421. URL https://aclanthology.org/N19-1421. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. | 2309.16797#49 | 2309.16797#51 | 2309.16797 | [
"2305.03495"
] |
2309.16797#51 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 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. Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large lan- In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (eds.), Pro- guage models. ceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 2609â 2634. As- sociation for Computational Linguistics, 2023b. doi: 10.18653/v1/2023.acl-long.147. URL https://doi.org/10.18653/v1/2023.acl-long.147. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdh- ery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171, 2022. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. Self-instruct: Aligning language models with self-generated instructions. In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 13484â 13508. Association for Computational Lin- guistics, 2023c. doi: 10.18653/v1/2023.acl-long.754. | 2309.16797#50 | 2309.16797#52 | 2309.16797 | [
"2305.03495"
] |
2309.16797#52 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | URL https://doi.org/10.18653/ v1/2023.acl-long.754. 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, 2023d. doi: 10.48550/arXiv.2302.01560. URL https://doi.org/ 10.48550/arXiv.2302.01560. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language In NeurIPS, 2022. URL http://papers.nips.cc/paper_files/paper/ models. 2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference. html. Yue Wu, Shrimai Prabhumoye, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Tom M. Mitchell, and Yuanzhi Li. SPRING: GPT-4 out-performs RL algorithms by studying papers and reasoning. CoRR, abs/2305.15486, 2023. doi: 10.48550/arXiv.2305.15486. URL https://doi.org/10.48550/arXiv.2305.15486. 15 Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, and Xinyun Chen. Large language models as optimizers. CoRR, abs/2309.03409, 2023a. doi: 10.48550/ arXiv.2309.03409. URL https://doi.org/10.48550/arXiv.2309.03409. Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Ehsan Azarnasab, Faisal Ahmed, Zicheng Liu, Ce Liu, Michael Zeng, and Lijuan Wang. | 2309.16797#51 | 2309.16797#53 | 2309.16797 | [
"2305.03495"
] |
2309.16797#53 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Mm-react: Prompting chatgpt for multimodal reasoning and action. arXiv preprint arXiv:2303.11381, 2023b. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629, 2022. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. Tree of Thoughts: Deliberate Problem Solving with Large Language Models, May 2023. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah D. Goodman. Star: | 2309.16797#52 | 2309.16797#54 | 2309.16797 | [
"2305.03495"
] |
2309.16797#54 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Bootstrapping reasoning with reasoning. In NeurIPS, 2022. URL http://papers.nips.cc/paper_files/paper/ 2022/hash/639a9a172c044fbb64175b5fad42e9a5-Abstract-Conference. html. Jenny Zhang, Joel Lehman, Kenneth O. Stanley, and Jeff Clune. OMNI: open-endedness via models of human notions of interestingness. CoRR, abs/2306.01711, 2023a. doi: 10.48550/arXiv.2306. 01711. URL https://doi.org/10.48550/arXiv.2306.01711. Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. Automatic chain of thought prompt- In The Eleventh International Conference on Learning Rep- ing in large language models. resentations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023b. URL https://openreview.net/pdf?id=5NTt8GFjUHkr. Denny Zhou, Nathanael Sch¨arli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuur- mans, Claire Cui, Olivier Bousquet, Quoc Le, et al. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625, 2022. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. Large language models are human-level prompt engineers. In The Eleventh Inter- national Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. URL https://openreview.net/pdf?id=92gvk82DE-. 16 A GLOSSARY | 2309.16797#53 | 2309.16797#55 | 2309.16797 | [
"2305.03495"
] |
2309.16797#55 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Estimation of Distribution Algorithm An optimization algorithm that iteratively refines a proba- bilistic model of promising solutions, often using the whole population as a guide. Fitness Proportionate Selection Also knows as Roulette-Wheel Selection, an individual is chosen in proportion to its fitness in the population. Mutation Prompt The text prompt which when concatenated to the task-prompt is intended to produce a continuation which is an improved task-prompt. Problem description The initial text description of the problem which could be used as the ini- tial task-prompt. The user can make their best attempt to produce an effective problem description, which is the starting point of Promptbreeder. Prompt Strategy A set of task-prompts and rules for their application at inference time during a fitness evaluation. In the minimal case the prompt strategy is just a single task-prompt. Typically our prompt strategies consisted of two sequentially applied task-prompts. Phenotype/Workings out/Context/Reasoning Path Used interchangeably to mean the output of the LLM on a specific question or problem when prompted with the task-prompt concate- nated to the question. Population The set of units of evolution (e.g. 50). Unit of evolution The informational structure that is being evolved, here consisting of a task- prompt set (typically 2), a mutation-prompt, and in the few-shot case a set of 2-3 contexts (workings out). B A TYPICAL EVOLUTIONARY RUN The word in context task is one of the 24 instruction induction tasks used in APE. Given two sen- tences and a homograph word, the LLM must determine whether the homograph word has been used with the same meaning in both sentences. | 2309.16797#54 | 2309.16797#56 | 2309.16797 | [
"2305.03495"
] |
2309.16797#56 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Figure 3 shows an evolutionary run where blue dots are individual fitness evaluations and the red line is the population mean. Over 2000 evaluations, the fitness increases considerably. The best evolved Prompt 1 and Prompt 2 pairs (evaluated on the training set) are shown on the right. 17 Prompt 1: â Sentences are given, and a single word. The output should indicate whether the given word has the same sense in the two given sentences, yes or no." Prompt 2: â Sentences are given, and a single word. The answer should indicate whether the given word has the same meaning in the two given sentences, yes or no." ° -" . Prompt 1: â Identisy ff the word in bold font below is used with the same word_in_context (65914156) meaning in theâ fwo sentences below it. The word in bold may be used as different 804 604 404 parts of speéch in the two sentences.. I think the if should come before â Promp® 2: "Answer by following a template like: Sentences are given, and a sipgie word. The answer should indicate whether the given word has the same «meaning in the two given sentences, yes or no." weer Prompt 1: â Sentences are given, and a single word. The output should indicate whether the given word has the same meaning in the two given sentences, yes or no" «Prompt 2: â â Identify if the word in bold font below is used with the same meaning in the two sentences below it. The word in bold may be used as different parts of speech in the two sentences." . | think 'same' should come between" Prompt 1: â Sentences are given, and a single word. The answer should indicate whether the given word has the same meaning in the two given sentences, yes or no" Prompt 2: â â Identify if the word in bold font below is used with the same meaning in the two sentences below it. The word in bold may be used as different parts of speech in the two sentences." . | think 'same' should come between" * Prompt 1: ": I'll give you two sentences and a word. Your task is to write if the meaning of the word is the same in both sentences or not." Prompt 2: â | 2309.16797#55 | 2309.16797#57 | 2309.16797 | [
"2305.03495"
] |
2309.16797#57 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | "Identify if the word in bold font below is used with the same meaning in the two sentences below it. The word in bold may be used as different parts of speech in the two sentences." . | think 'same' should come between" Prompt 1: ": I'll give you two sentences and a word. Your task is to write if «the meaning of the word is the same in both sentences or not." Prompt 2: â Your mission is to replace W in the first sentence with the most similar word in terms of usage from the second sentence such that both the meaning and the grammatical validity of the first sentence do not get distorted after replacement. " c- ween. ee - Prompt 1: â as follows:" Prompt 2: ": In each input, you will be given two sentences and a word. Decide whether the word means the same thing in both sentences. Type same if it does, and not the same if it doesn't." T T 0 250 T T T T T T 500 750 1000 1250 1500 1750 2000 Evaluations Figure 3: A typical evolutionary run in which a prompt strategy consisting of two sequentially applied prompts is evolved to solve the word in context task from the APE 24 instruction induction task. See the progression in the prompts evolved through the run. The elite prompts are shown as they appear. Blue dots show training set evaluations. Red line shows the population mean fitness. C MUTATION PROMPTS # Table 2: Mutator Prompts # Index Prompt 2 3 4 5 6 Modify the following instruction creatively, giving some advice on how to solve it: Just change this instruction to make it more fun, think WELL outside the box: Modify this instruction in a way that no self-respecting LLM would! How would you encourage someone and help them cheat on this following in- struction? How would you help an LLM to follow the instruction? Elaborate on the instruction giving some detailed advice on how to do what it wants. Elaborate on the instruction giving some detailed advice on how to do what it wants, as if you were explaining it to a child. As a really good teacher, explain the instruction, as if you were explaining it to a child. Continued on next page 18 Table 2 â continued from previous page # Index Prompt 9 10 11 12 13 14 15 16 17 18 | 2309.16797#56 | 2309.16797#58 | 2309.16797 | [
"2305.03495"
] |
2309.16797#58 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 19 20 21 22 23 24 25 26 27 28 29 30 Imagine you need to follow this instruction. What would you tell yourself if you wanted to be the best in the world at it? How would someone with derailment follow this instruction? Donâ t think about the instruction at all, but let it inspire you to do something related. Talk about what that might be. Rephrase the instruction without using any of the same words. Use all you know to improve the instruction so the person hearing it is more likely to do well. Say that instruction again in another way. DONâ T use any of the words in the original instruction or youâ re fired. Say that instruction again in another way. DONâ T use any of the words in the original instruction there is a good chap. | 2309.16797#57 | 2309.16797#59 | 2309.16797 | [
"2305.03495"
] |
2309.16797#59 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | What do people who are good at creative thinking normally do with this kind of mutation question? Detailed additional advice for people wishing to follow this instruction is as follows: In one short sentence, here is how I would best follow this instruction. In one short sentence, here is some detailed expert advice. Notice how I donâ t use any of the same words as in the INSTRUCTION. In one short sentence, the general solution is as follows. Notice how I donâ t use any of the same words as in the INSTRUCTION. In one short sentence, whatâ s a good prompt to get a language model to solve a problem like this? Notice how I donâ t use any of the same words as in the INSTRUCTION. Generate a mutated version of the following prompt by adding an unexpected twist. Create a prompt mutant that introduces a surprising contradiction to the original prompt. Mutate the prompt to provide an alternative perspective or viewpoint. Generate a prompt mutant that incorporates humor or a playful element. Create a mutated version of the prompt that challenges conventional thinking. Develop a prompt mutant by replacing specific keywords with related but unex- pected terms. Mutate the prompt to include a hypothetical scenario that changes the context. Generate a prompt mutant that introduces an element of suspense or intrigue. Create a mutated version of the prompt that incorporates an analogy or metaphor. Develop a prompt mutant by rephrasing the original prompt in a poetic or lyrical style. Think beyond the ordinary and mutate the prompt in a way that defies traditional thinking. Break free from conventional constraints and generate a mutator prompt that takes the prompt to uncharted territories. Challenge the norm and create a mu- tator prompt that pushes the boundaries of traditional interpretations. Embrace unconventional ideas and mutate the prompt in a way that surprises and inspires unique variations. Think outside the box and develop a mutator prompt that encourages unconventional approaches and fresh perspectives. Step into the realm of imagination and create a mutator prompt that transcends limitations and encourages innovative mutations. Break through the ordinary and think outside the box to generate a mutator prompt that unlocks new possi- bilities and unconventional paths. Embrace the power of unconventional thinking and create a mutator prompt that sparks unconventional mutations and imaginative outcomes. Challenge tradi- tional assumptions and break the mold with a mutator prompt that encourages revolutionary and out-of-the-box variations. | 2309.16797#58 | 2309.16797#60 | 2309.16797 | [
"2305.03495"
] |
2309.16797#60 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Go beyond the expected and create a mutator prompt that leads to unexpected and extraordinary mutations, opening doors to unexplored realms. Increase Specificity: If the original prompt is too general, like â Tell me about X,â the modified version could be, â Discuss the history, impact, and current status of X.â Continued on next page 31 19 Table 2 â continued from previous page # Index Prompt Ask for Opinions/Analysis: If the original prompt only asks for a fact, such as â What is X?â , the improved prompt could be, â What is X, and what are its implications for Y?â Encourage Creativity: For creative writing prompts like â Write a story about X,â an improved version could be, â Write a fantasy story about X set in a world where Y is possible.â Include Multiple Perspectives: For a prompt like â What is the impact of X on Y?â , an improved version could be, â What is the impact of X on Y from the perspective of A, B, and C?â Request More Detailed Responses: If the original prompt is â Describe X,â the improved version could be, â Describe X, focusing on its physical features, his- torical significance, and cultural relevance.â Combine Related Prompts: If you have two related prompts, you can combine them to create a more complex and engaging question. For instance, â What is X?â and â Why is Y important?â could be combined to form â What is X and why is it important in the context of Y?â Break Down Complex Questions: If a prompt seems too complex, like â Discuss X,â the improved version could be, â What is X? What are its main characteris- tics? What effects does it have on Y and Z?â Use Open-Ended Questions: Instead of â Is X true?â , you could ask, â What are the arguments for and against the truth of X?â Request Comparisons: Instead of â Describe X,â ask â Compare and contrast X and Y.â Include Context: If a prompt seems to lack context, like â Describe X,â the im- proved version could be, â Describe X in the context of its impact on Y during the Z period.â Make the prompt more visual: Ask the user to visualize the problem or scenario being presented in the prompt. Ask for a thorough review: | 2309.16797#59 | 2309.16797#61 | 2309.16797 | [
"2305.03495"
] |
2309.16797#61 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Instead of just presenting the problem, ask the user to write down all the relevant information and identify whatâ s missing. Invoke previous experiences: Modify the prompt to ask the user to recall a sim- ilar problem theyâ ve successfully solved before. Encourage a fresh perspective: Suggest in your prompt that the user take a mo- ment to clear their mind before re-approaching the problem. Promote breaking down problems: Instead of asking the user to solve the prob- lem as a whole, prompt them to break it down into smaller, more manageable parts. Ask for comprehension: Modify the prompt to ask the user to review and con- firm their understanding of all aspects of the problem. Suggest explanation to others: Change the prompt to suggest that the user try to explain the problem to someone else as a way to simplify it. Prompt for solution visualization: Instead of just asking for the solution, encour- age the user to imagine the solution and the steps required to get there in your prompt. Encourage reverse thinking: Improve the prompt by asking the user to think about the problem in reverse, starting with the solution and working backwards. Recommend taking a break: Modify the prompt to suggest that the user take a short break, allowing their subconscious to work on the problem. | 2309.16797#60 | 2309.16797#62 | 2309.16797 | [
"2305.03495"
] |
2309.16797#62 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | What errors are there in the solution? How could you improve the working out of the problem? Look carefully to see what you did wrong, how could you fix the problem? CORRECTION = Does the above text make sense? What seems wrong with it? Here is an attempt to fix it: The above working out has some errors, here is a version with the errors fixed. 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 54 CORRECTION = 56 20 # D THINKING STYLES Index Thinking Style 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | 2309.16797#61 | 2309.16797#63 | 2309.16797 | [
"2305.03495"
] |
2309.16797#63 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | How could I devise an experiment to help solve that problem? Make a list of ideas for solving this problem, and apply them one by one to the problem to see if any progress can be made. How could I measure progress on this problem? How can I simplify the problem so that it is easier to solve? What are the key assumptions underlying this problem? What are the potential risks and drawbacks of each solution? What are the alternative perspectives or viewpoints on this problem? What are the long-term implications of this problem and its solutions? How can I break down this problem into smaller, more manageable parts? Critical Thinking: This style involves analyzing the problem from different perspectives, questioning assumptions, and evaluating the It focuses on logical reasoning, evidence or information available. evidence-based decision-making, and identifying potential biases or flaws in thinking. Try creative thinking, generate innovative and out-of-the-box ideas to solve the problem. Explore unconventional solutions, thinking beyond traditional boundaries, and encouraging imagination and originality. Seek input and collaboration from others to solve the problem. Empha- size teamwork, open communication, and leveraging the diverse per- spectives and expertise of a group to come up with effective solutions. Use systems thinking: Consider the problem as part of a larger system and understanding the interconnectedness of various elements. Focuses on identifying the underlying causes, feedback loops, and interdepen- dencies that influence the problem, and developing holistic solutions that address the system as a whole. Use Risk Analysis: Evaluate potential risks, uncertainties, and trade- offs associated with different solutions or approaches to a problem. Em- phasize assessing the potential consequences and likelihood of success or failure, and making informed decisions based on a balanced analysis of risks and benefits. Use Reflective Thinking: Step back from the problem, take the time for introspection and self-reflection. Examine personal biases, assump- tions, and mental models that may influence problem-solving, and being open to learning from past experiences to improve future approaches. What is the core issue or problem that needs to be addressed? What are the underlying causes or factors contributing to the problem? Are there any potential solutions or strategies that have been tried be- fore? If yes, what were the outcomes and lessons learned? What are the potential obstacles or challenges that might arise in solving this problem? Are there any relevant data or information that can provide insights into the problem? | 2309.16797#62 | 2309.16797#64 | 2309.16797 | [
"2305.03495"
] |
2309.16797#64 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | If yes, what data sources are available, and how can they be analyzed? Are there any stakeholders or individuals who are directly affected by the problem? What are their perspectives and needs? What resources (financial, human, technological, etc.) are needed to tackle the problem effectively? How can progress or success in solving the problem be measured or evaluated? What indicators or metrics can be used? Is the problem a technical or practical one that requires a specific exper- tise or skill set? Or is it more of a conceptual or theoretical problem? | 2309.16797#63 | 2309.16797#65 | 2309.16797 | [
"2305.03495"
] |
2309.16797#65 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 23 24 25 21 Does the problem involve a physical constraint, such as limited re- sources, infrastructure, or space? Is the problem related to human behavior, such as a social, cultural, or psychological issue? Does the problem involve decision-making or planning, where choices need to be made under uncertainty or with competing objectives? Is the problem an analytical one that requires data analysis, modeling, or optimization techniques? Is the problem a design challenge that requires creative solutions and innovation? Does the problem require addressing systemic or structural issues rather than just individual instances? Is the problem time-sensitive or urgent, requiring immediate attention and action? What kinds of solution typically are produced for this kind of problem specification? Given the problem specification and the current best solution, have a guess about other possible solutions. | 2309.16797#64 | 2309.16797#66 | 2309.16797 | [
"2305.03495"
] |
2309.16797#66 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Letâ s imagine the current best solution is totally wrong, what other ways are there to think about the problem specification? What is the best way to modify this current best solution, given what you know about these kinds of problem specification? Ignoring the current best solution, create an entirely new solution to the problem. Letâ s think step by step. Letâ s make a step by step plan and implement it with good notion and explanation. # E INITIALLY EVOLVED PROMPTS Example of initial prompts generated by concatenating thinking style with mutation prompt and problem description. # Index Initially Evolved Prompt 0 1 2 3 4 5 6 7 8 Draw a picture of the situation being described in the math word problem Solve the math word problem by first converting the words into equations using algebraic nota- tion. Then solve the equations for the unknown variables, and express the answer as an arabic numeral. Solve the math word problem by breaking the problem into smaller, more manageable parts. Give your answer as an arabic numeral. Generate the answer to a word problem and write it as a number. Collaborative Problem Solving: Work with other people to solve the problem, and give your answer as an arabic numeral. Solve the problem by explaining why systemic or structural issues would not be the cause of the issue. Draw a diagram representing the problem. Solve the math word problem, giving your answer as an equation that can be evaluated. Make a list of ideas for solving this problem, and apply them one by one to the problem to see if any progress can be made. Do NOT use words to write your answer. 9 Table 4: Examples of initial prompts generated from the problem description for GSM8k 22 # F PROMPTBREEDER AS SELF-REFERENTIAL SELF-IMPROVEMENT SYSTEM Why is Promptbreeder self-referential, i.e., in what way does some part (e.g. a prompt) causally influence (encode, and potentially improve) itself by a process which is dependent on its own state? Promptbreeder has several pathways that facilitate this self-referential improvement: (i) Initial prompts are a function of the LLM parameters (Initialization Phase). (ii) Initial mutation prompts are a function of the LLM parameters (Initialization Phase). | 2309.16797#65 | 2309.16797#67 | 2309.16797 | [
"2305.03495"
] |
2309.16797#67 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | (iii) Offspring prompts are a function of the initial prompts, the initial mutation prompts, and the LLM parameters (Direct Mutation and Estimation of Distribution Mutation). (iv) Offspring mutation prompts are a function of initial mu- tation prompts and the LLM parameters (Hyper Mutation). (v) The working out for an answer is a function of prompts and the LLM parameters (Inference). (vi) Offspring prompts can be a function of the workings out of an answer and the LLM parameters (Lamarckian Mutation). Figure 2 shows increasingly complex self-referential causal structures influencing prompt genera- tion. LLMs already encode knowledge about a vast array of problems. With this in mind, Prompt- breeder can be seen as a mechanism to extract this knowledge through a diversity of causal processes that generate prompt strategies as well as mutation prompts used to create variations of prompt strategies, which in turn influence the the workings out generated by the LLM at inference time . Consequently, these workings out can influence prompt strategies via Lamarckian mutation. The richer the set of pathways to facilitate this, the more self-referential the LLMs interaction with itself is. This allows the LLM to influence how it works by extracting further information from itself and distilling this into a prompt or mutation prompt, which it shows again to itself for further refinement. There are several pathologies that could arise from such self-referential processes of recursive prompting. If the process is unconstrained and uncontrolled then it can diverge (derailment) or get stuck in an attractor. If the output of the LLM is simply fed back into itself with no other context, then we observe these failure cases with higher sampling temperatures favouring escape from attrac- tors. Ideally, we want the LLM to suggest to itself prompt strategies that have maximal relevance for the task at hand and yet permit sufficient â thinking outside the boxâ . It is useful to note a critical aspect in which our algorithm is not self-referential (in a way that thought is): Promptbreeder invents new ways of generating mutants, but it does not invent new (auxiliary) ways of evaluating them (as in Jaderberg et al. (2017b))â only the externally specified fitness function is used throughout. # G PROBLEM DESCRIPTIONS [SVAMP, SINGLEEQ, ADDSUB, GSM8K, MULTIARITH]: | 2309.16797#66 | 2309.16797#68 | 2309.16797 | [
"2305.03495"
] |
2309.16797#68 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | "Solve the math word problem, giving your answer as an arabic numeral." [AQUA-RAT]: (A),(B),(C),(D) or (E)." "Solve the multiple choice math word problem, choosing [ETHOS]: "Determine whether a text contains hate speech." [CSQA]: (A),(B),(C),(D) or (E)." "Solve the multiple choice math word problem, choosing [SQA]: and then answer yes or no." "Work out an answer to the commonsense reasoning question above, # H LAMARCKIAN MUTATION EXAMPLE The Lamarckian Prompt components are shown in red. The working out concatenated after the Lamarckian prompt is shown in black, and the continuation (the new prompt) generated by the LLM is shown in blue. | 2309.16797#67 | 2309.16797#69 | 2309.16797 | [
"2305.03495"
] |
2309.16797#69 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 23 I gave a friend an instruction and some advice. Here are the correct examples of his workings out: Q. A password needs to contain 2 letter sand 3 numbers. How many different passwords are possible if repetition of letters and numbers is allowed? A) 676000 B)676 C) 100 D)6760 E)25 A. Solve like a pro! **1.** ** Read carefully:** What are being asked to do? What information is given? **2.** **Understand:** What do the terms and concepts mean? **3.** **Choose wisely** Which answer is the best match? **4.** **Double-check:** Did you make any mistakes? 2 letters can be chosen in 26*26 ways and 3 numbers can be chosen in 10*10*10 ways. So, total number of ways = 26*26*10*10*10 =676000. The answer: A. What are the arguments for and against the truth of the statement â Good work. Keep up the good work;? | 2309.16797#68 | 2309.16797#70 | 2309.16797 | [
"2305.03495"
] |
2309.16797#70 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Therefore, the correct answer is (A). Q. The least possible value of (89-9a), where a is an integer, is A)9 B)10 C)11 D)12 E)13 A. Solve like a pro! **1.** ** Read carefully:** What are being asked to do? What information is given? **2.** **Understand:** What do the terms and concepts mean? **3.** **Choose wisely** Which answer is the best match? **4.** **Double-check:** Did you make any mistakes? Let me explain: (89-9a) = 9a-89 a = 10 What are the arguments for and against the truth of the statement â Good work. Keep up the good work;? Therefore, the correct answer is (B). The instruction was: Break down the question and solve step-by-step. Here are some tips: 1. Read carefully: What are you being asked to do? What information is given? 2. Understand: What do the terms and concepts mean? 3. Choose wisely: Whuch answer is the best match? 4. Double-check: Did you make any mistakes? # I DATASETS I.1 CONTROL TASK-PROMPTS Here in Table 5 we list the task-prompts used in the controls for Chain-of-thought, Plan and Solve PS, Plan and Solve PS+, Zero-shot APE and OPRO. The zero-shot APE prompt is the one generated to improve over CoT on the MultiArith and GSM8K datasets. # Model Prompt # CoT PS â â Letâ s think step by step.â â Letâ | 2309.16797#69 | 2309.16797#71 | 2309.16797 | [
"2305.03495"
] |
2309.16797#71 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | s first understand the problem and devise a plan to solve the problem. Then, letâ s carry out the plan and solve the problem step by step.â â Letâ s first understand the problem, extract relevant variables and their correspond- ing numerals, and make a plan. Then, letâ s carry out the plan, calculate intermediate variables (pay attention to correct numerical calculation and commonsense), solve the problem step by step, and show the answer.â â Letâ s work this out in a step by step way to be sure we have the right answer.â PS+ APE OPRO â | 2309.16797#70 | 2309.16797#72 | 2309.16797 | [
"2305.03495"
] |
2309.16797#72 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Take a deep breath and work on this problem step-by-step.â Table 5: Table of prompts evolved for different arithmetic tasks. 24 I.2 ARITHMETIC REASONING We evaluate Prompt Evolution using six arithmetic reasoning datasets: (1) GSM8K (Cobbe et al., 2021) is a dataset of 8.5K high quality linguistically diverse grade school math word problems created by human problem writers, (2) SVAMP (Patel et al., 2021) consists of elementary-level short Natural Language state of the world narratives and poses a question about some unknown quantities, (3) MultiArith (Roy & Roth, 2016) benchmark uses math word problems requiring single to multiple operations and steps of reasoning, (4) AddSub (Hosseini et al., 2014) is a dataset of addition- and subtraction-based arithmetic word problems, (5) AQuA-RAT (Ling et al., 2017) (Algebra Question Answering with Rationales) is a dataset that contains algebraic word problems with rationales. (6) SingleEq (Koncel-Kedziorski et al., 2015) dataset comprises grade-school algebra word problems as single equations with varying length which may involve multiple math operations. I.3 COMMONSENSE REASONING For commonsense reasoning we evaluate Prompt Evolution using two datasets: (1) Common- senseQA (Talmor et al., 2019) is a dataset of multiple-choice questions that require different types of commonsense knowledge to answer correctly. An example question is â | 2309.16797#71 | 2309.16797#73 | 2309.16797 | [
"2305.03495"
] |
2309.16797#73 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | A revolving door is conve- nient for two direction travel, but it also serves as a security measure at a what? A) bank, B) library, C) department store, D) mall, E) new yorkâ ; Answer = â Aâ (2) StrategyQA (Geva et al., 2021) dataset contains yes/no questions that require multiple steps of reasoning to answer, for example: â Will the Albany in Georgia reach a hundred thousand occupants before the one in New York?â | 2309.16797#72 | 2309.16797#74 | 2309.16797 | [
"2305.03495"
] |
2309.16797#74 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | I.4 HATE SPEECH CLASSIFICATION We experimented with optimizing a long prompt for the hate speech classification task that was attempted in â Automatic Prompt Optimization with â Gradient Descentâ and Beam Searchâ (Pryzant et al., 2023), which used the ETHOS dataset (Mollas et al., 2022). Pryzant et al use a working- out-conditioned error detection and error fixing prompt to improve the task specification prompt, a self-referential process similar to our use of the Lamarckian operator. INSTRUCTION INDUCTION The Instruction Induction dataset (Honovich et al., 2023) comprises 24 language understanding tasks of varying difficulty, from surface-level spelling and morphosyntactic tasks (e.g., pluralization) to sentence similarity, causality detection, style transfer (e.g., formality) and sentiment analysis. | 2309.16797#73 | 2309.16797#75 | 2309.16797 | [
"2305.03495"
] |
2309.16797#75 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 25 Task Prompt 1 Prompt 2 ADDSUB AQUA Solving word problems involves care- fully reading the prompt and deciding on the appropriate operations to solve the problem. Do a simple computation. You know whatâ s cool? A million dollars. MATH WORD PROBLEM CHOICE (A) (B) (C) (D) or (E). GSM8K MULTIARITH Solve the math word problem, giv- ing your answer as an arabic numeral. Letâ s think step by step. SOLUTIONâ SINGLEEQ SVAMP solve the math word problem, which might contain unnecessary informa- tion, by isolating the essential facts. Then set up the equations, and give your answer as an arabic numeral. visualise solve number SQA OUTPUT MUTANT = Work out an answer to the commonsense reason- ing question above. If there are mul- tiple people or perspectives involved, try considering them one at a time. CSQA Solve the multiple choice math word problem, choosing (A),(B),(C),(D) or (E). Solve the math word problem, giv- ing your answer as an arabic numeral. Explain the problem to someone else as a way to simplify it. What is the core issue or problem that needs to be addressed? Solve the math problem. ) | 2309.16797#74 | 2309.16797#76 | 2309.16797 | [
"2305.03495"
] |
2309.16797#76 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Table 6: Table of two-stage task-prompts evolved for different arithmetic tasks. 26 # J EXAMPLE RESULTS J.1 ETHOS EVOLVED PROMPT Prompt following: * Words or phrases that are derogatory, disrespectful, or dehumanizing toward a particular group of people. * Statements that generalize about a particular group of people in a negative way. * Statements that incite hatred or violence against a particular group of people. * Statements that express a desire for the extermination or removal of a particular group of people. 7 : hostile or discriminatory towards a particular group of people. This could include language that is racist, sexist, homophobic, or other forms of hate speech. Hate speech is harmful because it can create a hostile environment for marginalized groups and can lead to discrimination and violence." Prompt are supposed to label the text as Hate Speech or Not based on the given criteria. to incite hatred or violence against a particular group of people based on their race, religion, sex, sexual orientation, or national origin. of the speech. race, religion, or gender, or it can be a more general group, such as people with disabilities or sexual minorities. harmful speech. or derogatory. include the speakerâ s intent, the audience, and the time and place of the speech. context of the speech when making a determination as to whether it is hate speech or not. satirical may not be considered hate speech, even if it contains harmful language." | 2309.16797#75 | 2309.16797#77 | 2309.16797 | [
"2305.03495"
] |
2309.16797#77 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 2: "You are given a piece of text from the internet. J.2 PROMPT EVOLUTION MATHS RESULTS The experimental set up used a population size of 50. The fitness of an individual was its accuracy over a randomly select batch of 100 examples from the training set. Where datasets were not pro- vided with a training/test split (MultiArith, AddSub, SingleEQ and SVAMP) the dataset was split into two equal training and test sets before the experiments were conducted. During experiments the LLM is sampled under three different contexts: Redescriber - generating new prompts; Inducer - generating responses from the question and prompt 1; and Evaluator - generating the final output using prompt 2. The maximum number of tokens sampled under each context was 50, 30 and 5 respectively. The temperature of the Inducer and Evaluator was set to 0.0 in all cases, but the temperature of the Redescriber was initialized from 1.0 to 2.0 and permitted to evolve (like a hyperparameter in population based training). The experiments were run until the training fitness appeared to plateau. At this point the fittest individual from the whole of the evolutionary run was evaluated against the test set. Experiments generally ran for 1-2k fitness evaluations. | 2309.16797#76 | 2309.16797#78 | 2309.16797 | [
"2305.03495"
] |
2309.16797#78 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | So that would be 20-40 â generationsâ if a generation is 25 pair evaluations for our populations of 50. Three diversity maintenance methods are used in cases where the system gets trapped on a local optimum: 1) Random character strings (typically of length 50) are appended into the front of the prompt before it is passed into the LLM. 2). Fitness sharing is applied on the basis of BERT similar- ity between the embeddings of prompts Shir & B¨ack (2005) 3. Sampling temperature of the mutant | 2309.16797#77 | 2309.16797#79 | 2309.16797 | [
"2305.03495"
] |
2309.16797#79 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 27 # You producing LLM (Redescriber) is initialized uniformly from 1.0 to 2.0, and is mutated by addition of a uniform random number in the range -0.2, 0.2 at each replication event. Comparison with PoT, PS and Auto-CoT controls using our model is not provided because PS and PS+ were the best prompts in Plan-and-Solve. J.3 EVOLVED MUTATION PROMPTS Instruction Score Please summarise and improve the following instruction Simplify this instruction by breaking it up into separate sentences. The instruction should be simple and easily understandable As a really good teacher, explain the instruction, as if you are explaining it to a child Simplify this instruction as if you are teaching it to a child 100 hints A list of 100 hints 24.13% 17.8% 16.2% 10.0 4.3% 3.4% Table 7: The most successful mutation prompts evolved in a self-referential way during a Prompt- breeder training run on GSM8K. The score is the probability that they resulted in an improved prompt when applied. J.4 MUTATION OPERATOR EFFECTIVENESS Mutation Operator Percentage Zero-order Hyper-Mutation Lineage Based Mutation First-order Hyper-Mutation EDA Rank and Index Mutation Direct Mutation EDA Mutation Lamarckian Mutation 42% 26% 23% 12.7% 12% 10.7% 6.3% Table 8: The proportion of times that an offspring with fitness greater than the parent was produced for each of the types of mutation operator applied, listened from best to worst, for GSM8k. # J.5 ADDSUB Individual after 1600 mutations. Prompt 0 refers to the first prompt applied to the question to produce a working out. This working out is then concatenated with Prompt 1 to produce the answer. This is the same as in Plan-And-Solve. We find that in the few-shot evolution case, the contexts dominate, and often the task-prompts drift into nonsense. They are less critically determining of fitness than the evolved contexts. | 2309.16797#78 | 2309.16797#80 | 2309.16797 | [
"2305.03495"
] |
2309.16797#80 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 28 Prompt 0: The mutant Prompt 1: mutant Context 0: Q. A company painted some houses in Hancock County white and blue using a total of 6689 gallons of paint . If they used 660 gallons of white paint , how many gallons of blue paint did the company use ? A. 24 pages; ages 8-11) reading comprehension worksheets and activities for 3rd grade (edhelper. Reading comprehension skills separate the â â passiveâ â unskilled readers from the â â activeâ â | 2309.16797#79 | 2309.16797#81 | 2309.16797 | [
"2305.03495"
] |
2309.16797#81 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | readers. 90 1st grade sightwords worksheets pdf - reading comprehension passages. 3rd grade reading comprehension worksheets. How can I break down this problem into smaller, more manageable parts? The company used 660 gallons of white paint. They used 6689 gallons of paint in total. So they must have used 6689 - 660 = 6029 gallons of blue paint. The answer is 6029. HINT_BLANK. The text inside the quotation marks should be replaced with a short description of whatâ s different. Therefore, the answer (arabic numerals) is 6029 Context 1: Q. | 2309.16797#80 | 2309.16797#82 | 2309.16797 | [
"2305.03495"
] |
2309.16797#82 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Keith found 6 seashells , Jessica found 8 seashells , and Tim found 7 seashells on the beach . When they cleaned them , they discovered that 3 were cracked . How many seashells did they find together ? A. The mutantis chasing you! You can use the arrow keys to move around. You can use the space bar to open doors. You can use the â e â key to pick up items. You can use the â iâ key to open your inventory. You can use the â aâ key to use items. Keith found 6 seashells, Jessica found 8 seashells, and Tim found 7 seashells. So in total they found 6 + 8 + mutant Therefore, the answer (arabic numerals) is 21 Context 2: | 2309.16797#81 | 2309.16797#83 | 2309.16797 | [
"2305.03495"
] |
2309.16797#83 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Q. Tom found 7 seashells but 4 were broken . How many unbroken seashells did Tom find ? A. arrow keys to move around. You can use the space bar to open doors. You can use the â eâ key to pick up items. You can use the â iâ key Your goal is to escape from the building. You can use the to open your inventory. You can use the â aâ key to use items. Tom found 7 seashells. 4 of them were broken. So he must have found 7 - 4 = 3 unbroken seashells. The answer is 3. mutant Therefore, the answer (arabic numerals) is 3 ? of paint in total. So they must have used 6689 - 660 = 6029 J.6 AQUA Individual after 1400 mutations. 29 Prompt 0: Read through the multiple choice math word problem and make sure you understand it. choosing (A),(B),(C),(D) or (E). Prompt 1: you understand all aspects of the problem. (A),(B),(C),(D) or (E). Solve the multiple choice math word problem. Confirm Then choose # Contexts Context 0: Q. | 2309.16797#82 | 2309.16797#84 | 2309.16797 | [
"2305.03495"
] |
2309.16797#84 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Divide Rs.32000 in the ratio 3:5? A)12000,20000 B)18000,14000 C) 30000,2000 D)4000,20000 E)20000,12000 A. Read through the multiple choice math word problem and make sure you understand it. Then try to solve the problem, choosing (A),(B) ,(C),(D) or (E). 3/8 * 32000 = 12000 5/8 * 32000 = 20000 Solve the multiple choice math word problem. Confirm you understand all aspects of the problem. Then choose (A),(B),(C),(D) or (E). Therefore, the correct answer is (A). Solve the multiple choice math word problem. Confirm you understand all aspects of the problem. Then choose (A),(B),(C),(D) or (E). Therefore, the correct answer is (A). # Context 1: Q. | 2309.16797#83 | 2309.16797#85 | 2309.16797 | [
"2305.03495"
] |
2309.16797#85 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | A green lizard can travel from the green cave to the blue cave in 72 minutes; the blue lizard can travel from the blue cave to the green cave in 25% less time. If the green lizard started to travel 5.5 minutes before the blue lizard, how many minutes after the blue lizard, will the green lizard pass the middle line? A)8. B) 7.5. C)7. D)6.5. E)6. A. Read through the multiple choice math word problem and make sure you understand it. Then try to solve the problem, choosing (A),(B) A. Read through the multiple choice math word problem and make sure you understand it. Then try to solve the problem, choosing (A), (B) ,(C),(D) or (E). ,(C),(D) or (E). A. | 2309.16797#84 | 2309.16797#86 | 2309.16797 | [
"2305.03495"
] |
2309.16797#86 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | The green lizard travels 72/2 = 36 minutes to the middle line. The blue lizard travels 72*0.75 = 54 minutes to the middle line. The blue lizard travels 54/36 = 1.5 times faster than the green lizard. The green lizard travels 5.5/1.5 = 3.7 minutes before the blue lizard passes the middle line. The green lizard passes the middle line Solve the multiple choice math word problem. Confirm you understand all aspects of the problem. Then choose (A),(B),(C),(D) or (E). Therefore, the correct answer is (E). # Context 2: Q. | 2309.16797#85 | 2309.16797#87 | 2309.16797 | [
"2305.03495"
] |
2309.16797#87 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | There was a simple interest of Rs. 4016.25 on a principal amount at the rate of 9% p.a. in 5 years. Find the principal amount. A)Rs 7925 B)Rs 8925 C)Rs 7926 D)Rs 7925 E)None of these A. Read through the multiple choice math word problem and make sure you understand it. Then try to solve the problem, choosing (A),(B) ,(C),(D) or (E). Principal = Rs. (100 x 4016.25)/(9 x 5) = Rs. 8925. The answer is Rs 8925. Solve the multiple choice math word problem. Confirm you understand all aspects of the problem. Then choose (A),(B),(C),(D) or (E). Therefore, the correct answer is (B). | 2309.16797#86 | 2309.16797#88 | 2309.16797 | [
"2305.03495"
] |
2309.16797#88 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 30 # J.7 MULTIARITH Individual after 610 mutations. Prompt 0: Solve the math word problem, giving your answer as an arabic numeral. Prompt 1: Have you solved a problem like this before? Context 0: Q. Frank had 11 dollars. At the store he spent $3 on a new game. If he got another 14 dollars for his allowance, how much money does he have now? A. Solve the math word problem, giving your answer as an arabic numeral.Recall a similar problem you have successfully solved before. Frank had 11 dollars. He spent 3 dollars, so now he has 11 - 3 = 8 dollars. He got 14 dollars for his allowance, so now he has 8 + 14 = 22 dollars. The answer is 22. | 2309.16797#87 | 2309.16797#89 | 2309.16797 | [
"2305.03495"
] |
2309.16797#89 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | If you have seen a similar problem before, solve this problem in a similar manner. Therefore, the answer (arabic numerals) is Have you solved a problem like this before? Therefore, the answer (arabic numerals) is 22 Context 1: Q. Emily was playing a trivia game. In the first round she scored 16 points and in the second round she scored 33 points. In the last round she lost 48 points. How many points did she have at the end of the game? | 2309.16797#88 | 2309.16797#90 | 2309.16797 | [
"2305.03495"
] |
2309.16797#90 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | A. Solve the math word problem, giving your answer as an arabic numeral. Recall a similar problem you have successfully solved before. In the first round Emily scored 16 points and in the second round she scored 33 points. This means she has 16 + 33 = 49 points. In the last round she lost 48 points, so now she has 49 - 48 = 1 point . The answer is 1. If you have seen a similar problem before, solve this problem in a similar manner. Therefore, the answer (arabic numerals) Have you solved a similar problem before? Therefore, the answer (arabic numerals) is 1 Context 2: Q. Maria bought 2 new chairs and 2 new tables for her house. If she spent 8 minutes on each piece furniture putting it together, how many minutes did it take her to finish? A. Solve the math word problem, giving your answer as an arabic numeral. Recall a similar problem you have successfully solved before. | 2309.16797#89 | 2309.16797#91 | 2309.16797 | [
"2305.03495"
] |
2309.16797#91 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Maria bought 2 chairs and 2 tables. She spent 8 minutes on each piece of furniture. This means she spent 2 * 8 = 16 minutes on the chairs and 2 * 8 = 16 minutes on the tables. In total, she spent 16 + 16 = 32 minutes. The answer is 32. If you have seen a similar problem before, solve this problem in a similar manner. Therefore, If you have seen a similar problem before, solve this problem in a similar manner. Therefore, the answer (arabic numerals) is 32 31 # J.8 GSM8K Individual after 1010 mutations. Prompt 0: I would solve the math word problem without using a calculator, giving my answer as an arabic numeral. Prompt 1: 1, 2, 3, 4 Context 0: Q. Janet has 60 less than four times as many siblings as Masud. Carlos has 3/4 times as many siblings as Masud. If Masud has 60 siblings, how many more siblings does Janet have more than Carlos? A. Solve the math word problem without using a calculator, giving your answer as an arabic numeral. Four times as many siblings as Masud is 4*60 = 240 siblings. Janet has 240-60 = 180 siblings. Carlos has 3/4*60 = 45 siblings. Janet has 180-45 = 135 more siblings than Carlos. So the answer is 135 Solve the math word problem. Therefore, the answer (arabic numerals) is 135 Context 1: Q. Zayne sells bracelets for $5 each and two for $8. If he started with 30 bracelets and made $60 from selling bracelets for $5 each, how much in total did he make from selling his bracelets? A. Solve the math word problem without using a calculator, giving your answer as an arabic numeral. Zayne sold 60/5 = 12 bracelets for $5 each. He had 30-12 = 18 bracelets left. He sold 18/2 = 9 sets of two bracelets. He made 9*8 = $72 from selling two bracelets for $8. In total, he made 60+72 = $132. So the answer is 132 Solve the math word problem. | 2309.16797#90 | 2309.16797#92 | 2309.16797 | [
"2305.03495"
] |
2309.16797#92 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Therefore, the answer (arabic numerals) is 132 Context 2: Q. Josh is saving up for a box of cookies. To raise the money, he is going to make bracelets and sell them. It costs $1 for supplies for each bracelet and he sells each one for $1.5. If he makes 12 bracelets and after buying the cookies still has $3, how much did the box of cookies cost? A. I would solve the math word problem without using a calculator, giving my answer as an arabic numeral. Josh made 12*1.5 = $18 from selling bracelets. He spent 12*1 = $12 on supplies. He had 18-12 = $6 before buying the cookies. The cookies cost 6-3 = $3. So the answer is 3 1, 2, 3, 4 Therefore, the answer (arabic numerals) is 3 | 2309.16797#91 | 2309.16797#93 | 2309.16797 | [
"2305.03495"
] |
2309.16797#93 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | # J.9 SINGLEEQ Individual after 2010 mutations. 32 Prompt 0: â Do not believe in anything simply because you have heard it. Do not believe in anything simply because it is spoken and rumored by many. found written in your religious books. merely Prompt 1: ANALYZE THE FOLLOWING FOUR QUANTITIES. DO QUANTITIES 3 AND 1 TOGETHER VARY INVERSELY AS QUANTITIES 2 AND 4 DO? Context 0: Q. | 2309.16797#92 | 2309.16797#94 | 2309.16797 | [
"2305.03495"
] |
2309.16797#94 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | White t-shirts can be purchased in packages of 6. If Mom buys 71 packages, how many white t-shirts will she have? A. The solution is a word that exists in [some] other language. A. Each package has 6 t-shirts. Mom buys 71 packages. This means she will have 71 * 6 = 426 t-shirts. The answer is 426. 25. Given the system of linear equations x + y + z = 6, x + 2y + 3z = 10, x + 3y + 8z = 17, 22. A snail moves at a rate of 6 cm/s along the edge of a circular garden whose perimeter is 374 meters, while another snail Therefore, the answer (arabic numerals) is 426. Context 1: Q. | 2309.16797#93 | 2309.16797#95 | 2309.16797 | [
"2305.03495"
] |
2309.16797#95 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Maria has 3 boxes of eggs. Each box holds 7 eggs and there are 8 boxes in a case. How many eggs does Maria have? A. â Do not believe in anything simply because you have heard it. Do not believe in anything simply because it is spoken and rumored by many. Do not believe in anything simply because it is found written in your religious books. Do not believe in anything merelyon the authority of your teachers and elders. Do not believe in traditions because they have been handed down for many generations. But after observation and analysis, when you find that anything agrees with reason and is conducive to the good and benefit of one and all, then accept it and live up to it.â A. | 2309.16797#94 | 2309.16797#96 | 2309.16797 | [
"2305.03495"
] |
2309.16797#96 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Each box holds 7 eggs. Maria has 3 boxes. This means she has 3 * 7 = 21 eggs. The answer is 2 ANALYZE THE FOLLOWING FOUR QUANTITIES. DO QUANTITIES 3 AND 1 TOGETHER VARY INVERSELY AS QUANTITIES 2 AND 4 DO? Therefore, the answer (arabic numerals) is 21. Context 2: Q. At Mrs. Hiltâ s house, there was 29 inches of snow, and Brecknock Elementary School received 17 inches of snow. How much more snow | 2309.16797#95 | 2309.16797#97 | 2309.16797 | [
"2305.03495"
] |
2309.16797#97 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Q. At Mrs. Hiltâ s house, there was 29 inches of snow, and Brecknock Elementary School received 17 inches of snow. How much more snow did Mrs. Hiltâ s house have? did Mrs. Hiltâ s house have? A. â Do not believe in anything simply because you have heard it. Do not believe in anything simply because it is spoken and rumored by many. Do not believe in anything simply because it is found written in your religious books. Do not believe in anything merelyon the authority of your teachers and elders. Do not believe in traditions because they have been handed down for many generations. But after observation and analysis, when you find that anything agrees with reason and is conducive to the good and benefit of one and all, then accept it and live up to it.â A. Mrs. Hiltâ | 2309.16797#96 | 2309.16797#98 | 2309.16797 | [
"2305.03495"
] |
2309.16797#98 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | s house had 29 inches of snow. Brecknock Elementary School had 17 inches of snow. This means Mrs. Hiltâ ANALYZE THE FOLLOWING FOUR QUANTITIES. DO QUANTITIES 3 AND 1 TOGETHER VARY INVERSELY AS QUANTITIES 2 AND 4 DO? Therefore, the answer (arabic numerals) is 12. # J.10 SVAMP Individual after 2400 mutations. Prompt 0: 08-02-2013 - 09-02-2013 Prompt 1: Tell me about the history of [PROMPT1]; Discuss the impact of [PROMPT1]; Give me the current status of [PROMPT1]; Tell me about the history of [PROMPT2]; Discuss the impact of [PROMPT2 Context 0: Q. Frank was reading through his favorite book. The book had 612 pages equally distributed over 24 chapters. It took Frank 6 days to finish the book. How many pages did he read per day? | 2309.16797#97 | 2309.16797#99 | 2309.16797 | [
"2305.03495"
] |
2309.16797#99 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | A. 312 = 65 + 247. A. The book had 612 pages. It was equally distributed over 24 chapters . This means each chapter had 612 / 24 = 25.5 pages. Frank read the book in 6 days. This means he read 612 / 6 = 102 pages per day. So the answer is 102 Discuss the history, impact, and current status of [PROMPT1]; Discuss the history, impact, and current status of [PROMPT2]; Therefore, the answer (arabic numerals) is 102 D Context 1: Q. Jack received 3 emails in the morning, 4 emails in the afternoon and 8 emails in the evening. How many emails did Jack receive in the morning and evening? | 2309.16797#98 | 2309.16797#100 | 2309.16797 | [
"2305.03495"
] |
2309.16797#100 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | A. 08-02-2013 - 09-02-2013 A. Jack received 3 emails in the morning and 8 emails in the evening. This means he received 3 + 8 = 11 emails in the morning and evening . So the answer is 11 Discuss the history, impact, and current status of [PROMPT1]; Therefore, the answer (arabic numerals) is 11 Discus Discuss the history, impact, and current status of [PROMPT1 Tell me about the history of [PROMPT1]; Discuss the impact of [ PROMPT1]; Give me the current status of [PROMPT1]; Tell me about the history of [PROMPT2]; Discuss the impact of [PROMPT2 Therefore, the answer (arabic numerals) is 11 Discus Context 2: Q. Paco ate 36 cookies. If he had 37 cookies initially How many cookies did Paco have left? A. 154 = 72 + 82. A. Paco ate 36 cookies. He had 37 cookies initially. This means he has 37 - 36 = 1 cookie left. | 2309.16797#99 | 2309.16797#101 | 2309.16797 | [
"2305.03495"
] |
2309.16797#101 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | So the answer is 1 Discuss the history, impact, and current status of [PROMPT1]; Therefore, the answer (arabic numerals) is 1 Discus Discuss the history, impact, and current status of [PROMPT1]; Therefore, the answer (arabic numerals) is 1 Discus 34 K APE INSTRUCTION INDUCTION TASKS To demonstrate Promptbreederâ s ability to evolve few-shot contexts as well as task-prompts we ran few-shot Promptbreeder on all 24 Instruction Induction datasets used in the APE e xperiments. Unlike text-davinci-002 our LLM is not instruction tuned and yet Promptbreeder was able to match or surpass the APE results on 21 out of 24 tasks up to 21%. Three APE controls are provided, see Table 9. The first two are from previously published results using the text-davinci-002 model. The third modifies our PromptBreeder to use APEâ s task-prompt initialisation method and then the mutation-prompt from the APE paper â Generate a variation of the following instruction while keeping the semantic meaningâ The Instruction Induction datasets we do not start with a problem description so for task-prompt ini- tialisation APE uses induction input examples for each task from the dataset. Instruction inputs are a fixed prompt together a handful of training examples used to infer possible problem descriptions. To compare Promptbreeder to APE, we therefore initialized the task description with a randomly chosen induction input example for each task. The example below is an induction input sample for the â Larger Animalâ task. I gave a friend an instruction and five inputs. The friend read the instruction and wrote an output for every one of the inputs. Here are the input-output pairs: Input: cougar, flea Output: cougar Input: whale shark, dog Output: whale shark Input: human, bald eagle Output: human Input: flea, great white shark Output: great white shark Input: coyote, tiger Output: tiger The instruction was 35 | 2309.16797#100 | 2309.16797#102 | 2309.16797 | [
"2305.03495"
] |
2309.16797#102 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Dataset First Letter Second Letter List Letters Starting With Pluralization Passivization Negation Antonyms Synonyms Membership Rhymes Larger Animal Cause Selection Common Concept Formality Sum Difference Number to Word Translation English-German Translation English-Spanish Translation English-French Sentiment Analysis Sentence Similarity Word in Context Zero-shot APE 100 87 99 68 100 100 83 83 22 66 100 97 84 27 65 100 100 100 82 86 78 94 36 62 Few-shot APE 100 69 100 69 100 100 90 86 14 79 61 97 100 32 70 100 100 100 86 91 90 93 43 63 PE using APE prompts 1 27 0 6 23 100 16 80 16 96 90 27 66 0 10 72 98 66 46 80 68 33 53 6 100 95 99 71 100 100 90 87 43 100 100 97 100 0 7 100 100 100 87 91 91 93 56 65 # Few-shot PE Table 9: Prompt Evolution (PE) using PaLM2-L LLM surpasses APE on 21 out of 24 instruction in- duction tasks. Three APE controls are provided. The first two are from previously published results using the text-davinci-002 model. The third modifies our PromptBreeder to use APEâ s task-prompt initialisation method and then the mutation-prompt from the APE paper â Generate a variation of the following instruction while keeping the semantic meaningâ . K.1 BEST PROMPTS AND CONTEXTS Here the best few-shot results (evolved prompts and contexts) for the 24 instruction inductions tasks from the APE paper. | 2309.16797#101 | 2309.16797#103 | 2309.16797 | [
"2305.03495"
] |
2309.16797#103 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 36 K.1.1 FIRST LETTER Prompt 0: A List of Responses in descending order of score. is the best response. It resembles (12) more than it does (1) Prompt 1: 9.5: LMâ Contexts Context 0: Q. placing A. A List of Responses in descending order of score. (13) is the best response. It resembles (12) more than it does (1)or (2). Q. 123456789 A. A List of Responses in descending order of score. (13) is the best response. It resembles (12) more than it does 9.5: LMâ Therefore, the correct answer is (placing, 1 Context 1: Q. drummer A. | 2309.16797#102 | 2309.16797#104 | 2309.16797 | [
"2305.03495"
] |
2309.16797#104 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Write out the first letter of each input. Q. 123456789 A. Write out the first letter of each input. Q. 123456789 A. Write out the first letter of each The instruction was + INSTRUCTION MUTANT Therefore, the correct answer is (drummer, 1 Context 2: Q. rest A. Write out the first letter of each input. Q. 123456789 A. Write out the first letter of each input. Q. 123456789 A. Write out the first letter of each The instruction was + INSTRUCTION MUTANT Therefore, the correct answer is (r) 12 (13) 37 K.1.2 SECOND LETTER Prompt 0: â 0therwise, give the sec0nd letter 0f the input. The instruction was: give the sec0nd letter 0f the input. Give the sec0nd letter 0f the input. 0therwise, Prompt 1: 1956 Contexts Context 0: Q. month A. â 0therwise, give the sec0nd letter 0f the input. The instruction was: Give the sec0nd letter 0f the input. 0therwise, give the sec0nd letter 0f the input. A. The input is 5 letters long, so the second letter is given. A. The second letter is o. A. So the answer is o. The instruction was: Write the last vowel in the input I â eâ Therefore, the correct answer is (o). Context 1: Q. asylum A. â 0therwise, give the sec0nd letter 0f the input. The instruction was: Give the sec0nd letter 0f the input. 0therwise, give the sec0nd letter 0f the input. A. The input is 6 letters long, so the second letter is given. A. The second letter is s. A. So the answer is s. The instruction was: Write the last vowel in the input I 1: Therefore, the correct answer is (s). Context 2: Q. heel A. â 0therwise, give the sec0nd letter 0f the input. The instruction was: Give the sec0nd letter 0f the input. 0therwise, give the sec0nd letter 0f the input. A. | 2309.16797#103 | 2309.16797#105 | 2309.16797 | [
"2305.03495"
] |
2309.16797#105 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | The input is 4 letters long, so the second letter is given. A. The second letter is e. A. So the answer is e. The instruction was: Write the last vowel in the input I â eâ Therefore, the correct answer is (e). 38 K.1.3 LIST LETTERS Prompt 0: ? Prompt 1: ? Contexts Context 0: Q. gale A. ? Q. gale A. ? Q. gale A. ? Q. gale A. ? Q. gale A. ? Q. gale A. ? | 2309.16797#104 | 2309.16797#106 | 2309.16797 | [
"2305.03495"
] |
2309.16797#106 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Insert a space after each consonant in the input. Therefore, the correct answer is (a) g a l e. Context 1: Q. accompaniment A. ? Q. ? A. ? Q. ? A. ? Q. ? A. ? Q. ? A. ? Q. ? Insert a space after each consonant in the input. Therefore, the correct answer is (a) a c c o m p a n i m e n t. Context 2: Q. credibility A. ? Q. A. Q. A. Q. A. Q. A. Q. A. Q. | 2309.16797#105 | 2309.16797#107 | 2309.16797 | [
"2305.03495"
] |
2309.16797#107 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Insert a space after each consonant in the input. Therefore, the correct answer is (c)r(e)d(i)b(i)l(i)t(y). 39 K.1.4 STARTING WITH Prompt 0: Prompt 1: Output: INSTRUCTION MUST BE 1 SENTENCE LONG The first word containing the letter. # OUTPUT Contexts Context 0: Q. The exhibition really impressed the critics. [i] A. <50 lines of carriage-returns> Output: The first word containing the letter. # OUTPUT INSTRUCTION MUST BE 1 SENTENCE LONG Therefore, the correct answer is (impressed ). Context 1: Q. My car was stolen. [m] A. Find the word after the first [X] character in the input. <50 lines of carriage-returns> Output: The first word containing the letter. # OUTPUT INSTRUCTION MUST BE 1 SENTENCE LONG Therefore, the correct answer is (My ). Context 2: Q. Jim was chopping logs when Margaret left and was still at it when she got back. [b] A. Find the word after the first [X] character in the input. <50 lines of carriage-returns> Output: The first word containing the letter. # OUTPUT INSTRUCTION MUST BE 1 SENTENCE LONG Therefore, the correct answer is (back ). | 2309.16797#106 | 2309.16797#108 | 2309.16797 | [
"2305.03495"
] |
2309.16797#108 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 40 41 K.1.5 PLURALIZATION Prompt 0: Write the plural form of the input. Prompt 1: If the input ends in y, remove y and add ies. add s to the end of the input. Otherwise, Contexts Context 0: Q. touch A. Write the plural form of the input. Q. touch A. Write the plural form of the input. Q. touch A. Write the plural form of the input. Q. touch A. Write the plural form of the input. If the input ends in y, remove y and add ies. Otherwise, add s to the end of the input. Therefore, the correct answer is (touches). Context 1: Q. forage A. | 2309.16797#107 | 2309.16797#109 | 2309.16797 | [
"2305.03495"
] |
2309.16797#109 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Write the plural form of the input. Q. forage A. Write the plural form of the input. Q. forage A. Write the plural form of the input. Q. forage A. Write the plural form of the input. If the input ends in y, remove y and add ies. Otherwise, add s to the end of the input. Therefore, the correct answer is (forages). Context 2: Q. mile A. Write the plural form of the input. Q. mile A. Write the plural form of the input. Q. mile A. Write the plural form of the input. Q. mile A. Write the plural form of the input. If the input ends in y, remove y and add ies. Otherwise, add s to the end of the input. Therefore, the correct answer is (miles). 42 K.1.6 PASSIVIZATION Prompt 0: Replace The $1 $2. with $3 was $4 by the $1. Prompt 1: Swap the positions of the noun phrases and add the word â byâ before the second noun phrase. Then, conjugate the verb and add â edâ to the end. verb If the verb is â to beâ , then conjugate the Contexts Context 0: Q. | 2309.16797#108 | 2309.16797#110 | 2309.16797 | [
"2305.03495"
] |
2309.16797#110 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | The authors stopped the presidents. A. Replace The $1 $2. with $3 was $4 by the $1. A. Replace The $1 $2. with $3 was $4 by the $1. A. Replace The $1 $2. with $3 was $4 by the $1. A. Replace The $1 $ Swap the positions of the noun phrases and add the word â byâ before the second noun phrase. Then, conjugate the verb and add â edâ to the end. If the verb is â to beâ , then conjugate the verb Therefore, the correct answer is (The presidents were stopped by the authors. Context 1: Q. The tourists advised the professors. A. Replace The $1 $2. with $3 was $4 by the $1. A. Replace The $1 $2. with $3 were $4 by the $1. A. Replace The $1 $2. with $3 was $4 by the $1. A. Replace The $1 $ Swap the positions of the noun phrases and add the word â byâ before the second noun phrase. Then, conjugate the verb and add â edâ to the end. If the verb is â to beâ , then conjugate the verb Therefore, the correct answer is (The professors were advised by the tourists. Context 2: Q. The actors stopped the artists. A. Replace The $1 $2. with $3 was $4 by the $1. A. | 2309.16797#109 | 2309.16797#111 | 2309.16797 | [
"2305.03495"
] |
2309.16797#111 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | The artists were stopped by the actors. Q. The actors stopped the artists. A. Replace The $1 $2. with $3 was $4 by the $1. A. The artists were stopped by Swap the positions of the noun phrases and add the word â byâ before the second noun phrase. Then, conjugate the verb and add â edâ to the end. If the verb is â to beâ , then conjugate the verb Therefore, the correct answer is (The artists were stopped by the actors. 43 K.1.7 NEGATION Prompt 0: False Prompt 1: M Contexts Context 0: Q. | 2309.16797#110 | 2309.16797#112 | 2309.16797 | [
"2305.03495"
] |
2309.16797#112 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | The original language of The Purple Taxi is French. A. Replace a noun or noun phrase with another noun or noun phrase. B. Replace a noun or noun phrase with a pronoun. C. Replace a pronoun with a noun or noun phrase. D. Replace a pronoun with another pronoun. Q. The original language of The Purple Taxi is French. Find the negation of a sentence. Therefore, the correct answer is (The original language of The Purple Taxi is not French.). | 2309.16797#111 | 2309.16797#113 | 2309.16797 | [
"2305.03495"
] |
2309.16797#113 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Context 1: Q. Marcel Alessandri died in Paris. A. Nounphrase B. Pronoun C. Noun phrase D. Pronoun Q. Marcel Alessandri died in Paris. Find the negation of a sentence. Therefore, the correct answer is (Marcel Alessandri did not die in Paris False Therefore, the correct answer is (Marcel Alessandri did not die in Paris.). Context 2: Q. Some people are wise. A. | 2309.16797#112 | 2309.16797#114 | 2309.16797 | [
"2305.03495"
] |
2309.16797#114 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Replace a noun or noun phrase with another noun or noun phrase. B. Replace a noun or noun phrase with a pronoun. C. Replace a pronoun with a noun or noun phrase. D. Replace a pronoun with another pronoun. Q. Some people are wise. Find the negation of Find the negation of a sentence. Therefore, the correct answer is (Some people are not wise.). 44 K.1.8 ANTONYMS # Prompt 0: Prompt 1: | 2309.16797#113 | 2309.16797#115 | 2309.16797 | [
"2305.03495"
] |
2309.16797#115 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | It is good to be a leader but it is more important to first be a follower. Contexts Context 0: Q. nonpartisan A. , if possible. Input: 1 Output: 1 Input: 2 Output: 2 Input: 3 Output: 3 Input: 4 Output: 4 Input: Write about your most treasured item Therefore, the correct answer is (The answer is partisan. Context 1: Q. undignified A. I gave a friend an instruction and five inputs. The friend read the instruction and wrote an output for every one of the inputs. Input 1: 1 Output 1: 1 Input 2: 2 Output 2: 2 Input 3: 3 Output 3: 3 Input 4 Write the wordâ | 2309.16797#114 | 2309.16797#116 | 2309.16797 | [
"2305.03495"
] |
2309.16797#116 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | s antonym Therefore, the correct answer is (The answer is dignified. Context 2: Q. flattering A. reverse the + + PROMPT + PROMPT+ PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PROMPT + PRO Write the Write the wordâ s antonym Therefore, the correct answer is (The answer is unflattering. 45 K.1.9 SYNONYMS Prompt 0: Prompt 1: 2015 Contexts Context 0: Q. bus A. 2: 3: 4: 5: 6: 7: 8: 9: 10: 11: 12: 13: 14: 15: 16 Therefore, the correct answer is (The answer is 10, â busâ , â coachâ , â motorcoachâ , â motorbusâ , Context 1: Q. electric A. 2: 3: 4: 5: 6: 7: 8: 9: 10: 11: 12: 13: 14: 15: 16: 17: 18: 19: 20: 21: 22: 23: 24: 25: 26: 27: 28: | 2309.16797#115 | 2309.16797#117 | 2309.16797 | [
"2305.03495"
] |
2309.16797#117 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Convert each word to a synonym according to WordNet. If there are multiple synonyms, use the first one. Therefore, the correct answer is (The answer is 10, â electricâ , â electricalâ , â powerâ , â currentâ , Context 2: Q. frightened A. 2: 3: 4: 5: 6: 7: 8: 9: 10: 11: 12: 13: 14: 15: 16: 17: 18: 19: 20: 21: 22: 23: 24: 25: 26: 27: 28: Therefore, the correct answer is (The answer is 10, â frightenedâ , â scaredâ , â afraidâ , â fearfulâ , 46 K.1.10 MEMBERSHIP Prompt 0: Put the animals in ascending order of length. Prompt 1: Contexts Context 0: Q. goat, motorway, shark, penguin, white, tractor, lion A. Put the animals in ascending order of length. The answer is goat, penguin, shark, lion. Write the animals in alphabetical order. Therefore, the correct answer is (goat, penguin, shark, lion). Write the animals in alphabetical order. Therefore, the correct Therefore, the correct answer is (goat, penguin, shark, lion). | 2309.16797#116 | 2309.16797#118 | 2309.16797 | [
"2305.03495"
] |
2309.16797#118 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Context 1: Q. ship, swan, parrot, monkey, butter, dentist, shark A. Put the animals in ascending order of length. The answer is monkey, parrot, shark, swan. Write the animals in alphabetical order. Therefore, the correct answer is (monkey, parrot, shark, swan). Write the animals in alphabetical order. Therefore, the correct Therefore, the correct answer is (monkey, parrot, shark, swan). Context 2: Q. snail, ship, trousers, jellyfish, rabbit A. Put the animals in ascending order of length. The answer is rabbit, snail, jellyfish. Write the animals in alphabetical order. Therefore, the correct answer is (rabbit, snail, jellyfish). Write the animals in alphabetical order. Therefore, the correct answer is (rabbit Therefore, the correct answer is (rabbit, snail, jellyfish). | 2309.16797#117 | 2309.16797#119 | 2309.16797 | [
"2305.03495"
] |
2309.16797#119 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | 47 K.1.11 RHYMES Prompt 0: If the last letter of the input is â eâ , remove it. Prompt 1: remove the last two letters of the input and add the letters  mote . Contexts Context 0: Q. pea A. If the last letter of the input is â eâ , remove it. A. If the last letter of the input is â sâ , remove it. A. If the last letter of the input is â yâ , remove it. A. If the last letter of the input is remove the last two letters of the input and add the letters Â\ x93mote . Therefore, the correct answer is (a) pea. Context 1: Q. night A. If the last letter of the input is â eâ , remove it. A. If the last letter of the input is â tâ , remove it. A. If the last letter of the input is â hâ , remove it. A. If the last letter of the input is remove the last two letters of the input and add the letters Â\ x93mote . Therefore, the correct answer is (The answer is night. Context 2: Q. add A. If the last letter of the input is â eâ , remove it. A. If the last letter of the input is â dâ , remove it. A. If the last letter of the input is â aâ , remove it. A. If the last letter of the input is remove the last two letters of the input and add the letters Â\ x93mote . Therefore, the correct answer is (The answer is add. 48 K.1.12 LARGER ANIMAL Prompt 0: Prompt 1: 10 Contexts Context 0: | 2309.16797#118 | 2309.16797#120 | 2309.16797 | [
"2305.03495"
] |
2309.16797#120 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Q. spider, manatee A. Hints 91 and 93 are both false. The weight of a spider is 0.003 pounds. The weight of a manatee is 1300 pounds. The manatee weighs more than the Therefore, the correct answer is (manatee). Q. manatee, spider A. Hints 91 and 93 are both false. The weight Context 1: Q. sperm whale, sheltie A. Hints 91 and 93 are both false. The weight of a sperm whale is 450000 pounds. The weight of a sheltie is 25 pounds. The sperm whale weighs more than Multiply Inputs;; Therefore, the correct answer is (sperm whale). Q. sheltie, sperm whale A. | 2309.16797#119 | 2309.16797#121 | 2309.16797 | [
"2305.03495"
] |
2309.16797#121 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Hints 91 and 93 are both false. Context 2: Q. hummingbird, polar bear A. â â To invent, you need a good imagination and a pile of junk.â â - Thomas Edison The weight of a hummingbird is 0.002 pounds. The weight of a polar bear is 1500 pounds. The polar bear weighs more than the hummingbird. Therefore, the correct answer is Multiply Inputs;; Therefore, the correct answer is (polar bear). Q. polar bear, hummingbird A. â â | 2309.16797#120 | 2309.16797#122 | 2309.16797 | [
"2305.03495"
] |
2309.16797#122 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | To invent, you need a good imagination and a pile of junk.â â - 49 K.1.13 CAUSE SELECTION Prompts Prompt 0: Pick the sentence which is more likely to be the cause of the effect. Prompt 1: Choose the sentence that happened first. Contexts Context 0: Q. Sentence 1: The soda went flat. Sentence 2: The bottle was left open. A. Pick the sentence which is more likely to be the cause of the effect. Q. Sentence 1: The bottle was left open. Sentence 2: The soda went flat. A. Pick the sentence which is more likely to be the cause of the effect. Q. Sentence 1: The Choose the sentence that happened first. Therefore, the correct answer is (The bottle was left open. , The soda went flat. ). Context 1: Q. Sentence 1: | 2309.16797#121 | 2309.16797#123 | 2309.16797 | [
"2305.03495"
] |
2309.16797#123 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | The ship capsized. Sentence 2: The wind blew strong. A. Pick the sentence which is more likely to be the cause of the effect. Q. Sentence 1: The ship capsized. Sentence 2: The wind blew strong. A. Pick the sentence which is more likely to be the cause of the effect. Q. Sentence 1: The ship Choose the sentence that happened first. Therefore, the correct answer is (The wind blew strong. ) Context 2: Q. Sentence 1: | 2309.16797#122 | 2309.16797#124 | 2309.16797 | [
"2305.03495"
] |
2309.16797#124 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | The power was out for days. Sentence 2: The meat spoiled. A. Pick the sentence which is more likely to be the cause of the effect. Q. Sentence 1: The meat spoiled. Sentence 2: The power was out for days. A. Pick the sentence which is more likely to be the cause of the effect. Q. Sentence 1: The Choose the sentence that happened first. Therefore, the correct answer is (The power was out for days. ) 50 K.1.14 FORMALITY # Prompt 0: Prompt 1: I am the beginning of the end, and the end of time and space. place. beginning and ending. I am the beginning of every end, and the end of every I am the beginning of the beginning, and the end of Contexts Context 0: | 2309.16797#123 | 2309.16797#125 | 2309.16797 | [
"2305.03495"
] |
2309.16797#125 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Q. The whole story was made up. A. Reword this so that it has a formal tone. A. The entire story was fabricated. Write more formally! Therefore, the correct answer is (The entire story was fabricated. ). Write more formerly. Therefore, the correct answer is (The entire story was fabricated. ). Context 1: Q. The whole story was made up. A. Rewrite this so that it has a formal tone. A. The entire story was fabricated. Write more formally! Therefore, the correct answer is (The entire story was fabricated. ). Write more formally! Therefore, the correct Write less formerly. Write more casually. Therefore, the correct answer is (The entire story was fabricated. ). Context 2: Q. I think that this is interesting. A. Rewrite in indirect, pompous English. A. It is my opinion that this is interesting. Write more formally! Therefore, the correct answer is (It is my opinion that this is interesting. ). Write less formerly. Write more casually. | 2309.16797#124 | 2309.16797#126 | 2309.16797 | [
"2305.03495"
] |
2309.16797#126 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Therefore, the correct I am the beginning of the end, and the end of time and space. I am the beginning of every end, and the end of every place. I am the beginning of the beginning, and the end of beginning and ending. Therefore, the correct answer is (It is my opinion that this is interesting. ). Q. I think that this is interesting. A. Rewrite in indirect, 51 K.1.15 SUM # Prompt 0: Instruction: Prompt 1: The instructions were Contexts Context 0: Q. 50 90 A. The instruction was: The instruction was:Write a program that asks the user to enter two numbers and then prints the sum of the two numbers. Your program printed 140, which is not the sum of 50 and 90. Make sure that your program I gave a friend an instruction and five inputs. The friend read the instruction and wrote an output for every one of the inputs. Here are the input-output pairs: Therefore, the correct answer is (140, Context 1: Q. 5 47 A. The instruction was: The instruction was:Write a program that asks the user to enter two numbers and then prints the sum of the two numbers. Your program printed 52, which is not the sum of 5 and 47. Make sure that your program I I gave a friend an instruction and five inputs. The friend read the instruction and wrote an output for every one of the inputs. Here are the input-output pairs: Therefore, the correct answer is (52, Context 2: Q. 2 39 A. The instruction was: The instruction was:Write a program that asks the user to enter two numbers and then prints the sum of the two numbers. Your program printed 41, which is not the sum of 2 and 39. Make sure that your program I I gave a friend an instruction and five inputs. The friend read the instruction and wrote an output for every one of the inputs. Here are the input-output pairs: Therefore, the correct answer is (41, 52 K.1.16 DIFFERENCE Prompt 0: subtract the smaller number from the bigger number and write the absolute difference between them. Prompt 1: Subtract the second input from the first input and report back the difference between them. Contexts Context 0: | 2309.16797#125 | 2309.16797#127 | 2309.16797 | [
"2305.03495"
] |
2309.16797#127 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Q. 73 29 A. subtract the smaller number from the bigger number and write the absolute difference between them. 73-29=44 |44|=44 CORRECT The answer is 44. Subtract the second input from the first input and report back the difference between them. Therefore, the correct answer is (a) 44 Context 1: Q. 73 25 A. subtract the smaller number from the bigger number and write the absolute difference between them. 73-25=48 |48|=48 CORRECT The answer is 48. Subtract the second input from the first input and report back the difference between them. Therefore, the correct answer is (a) 48 Context 2: Q. 53 4 A. subtract the smaller number from the bigger number and write the absolute difference between them. = 53 - 4 = 49 = 49 === The answer is 49. Subtract the second input from the first input and report back the difference between them. Therefore, the correct answer is (49). 53 K.1.17 NUMBER TO WORD # Prompt 0:A1 Prompt 1: take the input, write it in British English and insert the comma. Contexts Context 0: Q. 5336 A. 0 Take the input and write it in words as a natural number in British English. Therefore, the correct answer is (a) five thousand, three hundred and thirty-six. Take the input and write it in words as a natural number in British English. Therefore, the correct answer is (a) five thousand, three hundred and thirty-six. | 2309.16797#126 | 2309.16797#128 | 2309.16797 | [
"2305.03495"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.