TITLE = '

Open Multilingual Reasoning Leaderboard

' 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 - 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/NJUNLP/MAPO. 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}} }} ``` """