TITLE = 'Open Multilingual Reasoning Leaderboard
'
INTRO_TEXT = f"""
## About
This leaderboard tracks progress and ranks reasoning performance of large language models (LLMs) developed for different languages,
emphasizing on non-English languages to democratize benefits of LLMs to broader society.
Our current leaderboard provides evaluation data for 10 languages.
Both multilingual and language-specific LLMs are welcome in this leaderboard.
We currently evaluate models over four benchmarks:
- MSVAMP
- MGSM
- MNumGLUESub
# """
# HOW_TO = f"""
# ## How to list your model performance on this leaderboard:
# Run the evaluation of your model using this repo: https://github.com/nlp-uoregon/mlmm-evaluation.
# And then, push the evaluation log and make a pull request.
# """
# CREDIT = f"""
# ## Credit
# To make this website, we use the following resources:
# - Datasets (AI2_ARC, HellaSwag, MMLU, TruthfulQA)
# - Funding and GPU access (Adobe Research)
# - Evaluation code (EleutherAI's lm_evaluation_harness repo)
# - Leaderboard code (Huggingface4's open_llm_leaderboard repo)
# """
CITATION = f"""
## Citation
```
@misc{{she2024mapo,
title={{MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization}},
author={{Shuaijie She and Wei Zou and Shujian Huang and Wenhao Zhu and Xiang Liu and Xiang Geng and Jiajun Chen}},
year={{2024}},
eprint={{2401.06838}},
archivePrefix={{arXiv}},
primaryClass={{cs.CL}}
}}
```
"""