{
 "id": "CohereLabsCommunity/multilingual-reward-bench",
 "owner": "CohereLabsCommunity",
 "name": "multilingual-reward-bench",
 "downloads": 1827,
 "likes": 37,
 "last_modified": "2025-07-23T03:38:25.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{gureja-etal-2025-rewardbench,\n    title = \"{M}-{R}eward{B}ench: Evaluating Reward Models in Multilingual Settings\",\n    author = \"Gureja, Srishti  and\n      Miranda, Lester James Validad  and\n      Islam, Shayekh Bin  and\n      Maheshwary, Rishabh  and\n      Sharma, Drishti  and\n      Winata, Gusti Triandi  and\n      Lambert, Nathan  and\n      Ruder, Sebastian  and\n      Hooker, Sara  and\n      Fadaee, Marzieh\",\n    editor = \"Che, Wanxiang  and\n      Nabende, Joyce  and\n      Shutova, Ekaterina  and\n      Pilehvar, Mohammad Taher\",\n    booktitle = \"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2025\",\n    address = \"Vienna, Austria\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.acl-long.3/\",\n    pages = \"43--58\",\n    ISBN = \"979-8-89176-251-0\",\n    abstract = \"Reward models (RMs) have driven the state-of-the-art performance of LLMs today by enabling the integration of human feedback into the language modeling process. However, RMs are primarily trained and evaluated in English, and their capabilities in multilingual settings remain largely understudied. In this work, we conduct a systematic evaluation of several reward models in multilingual settings. We first construct the first-of-its-kind multilingual RM evaluation benchmark, M-RewardBench, consisting of 2.87k preference instances for 23 typologically divers",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "04120fd1f0ef4faed0d6fd4fb632a14476fb0498",
 "stated_evidence": "https://huggingface.co/datasets/CohereLabsCommunity/multilingual-reward-bench/blob/04120fd1f0ef4faed0d6fd4fb632a14476fb0498/README.md",
 "file_evidence": "https://huggingface.co/datasets/CohereLabsCommunity/multilingual-reward-bench/tree/04120fd1f0ef4faed0d6fd4fb632a14476fb0498",
 "card_nc": false
}