|
TITLE = '<h1 align="center" id="space-title">Open Multilingual Reasoning Leaderboard</h1>' |
|
|
|
INTRO_TEXT = f""" |
|
## About |
|
|
|
This leaderboard tracks and ranks the reasoning performance of the leading, most advanced multilingual reasoning LLMs on three multilingual mathematical reasoning benchmarks. Each benchmark contains 10 languages: Bengali, Swedish, Thailand, Chinese, Japan, Russian, French, Spanish, German and English. |
|
Both multilingual and language-specific LLMs are welcome in this leaderboard. |
|
|
|
## 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://huggingface.co/datasets/kevinpro/MNumGLUESub" 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/NJUNLP/MAPO" target="_blank">https://github.com/NJUNLP/MAPO</a>. |
|
|
|
And then, push the evaluation log and make a pull request. |
|
""" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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}} |
|
}} |
|
``` |
|
""" |
|
|