content.py

TITLE = '<h1 align="center" id="space-title">Open Multilingual Reasoning Leaderboard</h1>'

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:

- <a href="https://huggingface.co/datasets/Mathoctopus/MSVAMP" target="_blank">  MSVAMP </a>
- <a href="https://huggingface.co/datasets/juletxara/mgsm" target="_blank">  MGSM </a>
- <a href="https://arxiv.org/abs/2009.03300" target="_blank">  MNumGLUESub </a> 

# """

# HOW_TO = f"""
# ## How to list your model performance on this leaderboard:

# Run the evaluation of your model using this repo: <a href="https://github.com/nlp-uoregon/mlmm-evaluation" target="_blank">https://github.com/nlp-uoregon/mlmm-evaluation</a>.

# 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}}
}}
```
"""