{
 "id": "VISAI-AI/nitibench",
 "owner": "VISAI-AI",
 "name": "nitibench",
 "downloads": 513,
 "likes": 8,
 "last_modified": "2025-11-26T21:18:08.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "sentence-similarity",
  "text-generation"
 ],
 "citation": "@inproceedings{akarajaradwong-etal-2025-nitibench,\n    title = \"{N}iti{B}ench: Benchmarking {LLM} Frameworks on {T}hai Legal Question Answering Capabilities\",\n    author = \"Akarajaradwong, Pawitsapak  and\n      Pothavorn, Pirat  and\n      Chaksangchaichot, Chompakorn  and\n      Tasawong, Panuthep  and\n      Nopparatbundit, Thitiwat  and\n      Pratai, Keerakiat  and\n      Nutanong, Sarana\",\n    editor = \"Christodoulopoulos, Christos  and\n      Chakraborty, Tanmoy  and\n      Rose, Carolyn  and\n      Peng, Violet\",\n    booktitle = \"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2025\",\n    address = \"Suzhou, China\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.emnlp-main.1739/\",\n    doi = \"10.18653/v1/2025.emnlp-main.1739\",\n    pages = \"34292--34315\",\n    ISBN = \"979-8-89176-332-6\",\n    abstract = \"Large language models (LLMs) show promise in legal question answering (QA), yet Thai legal QA systems face challenges due to limited data and complex legal structures. We introduce NitiBench, a novel benchmark featuring two datasets: (1) NitiBench-CCL, covering Thai financial laws, and (2) NitiBench-Tax, containing Thailand{'}s official tax rulings. Our benchmark also consists of specialized evaluation metrics suited for Thai legal QA. We evaluate retrieval-augmented generation (RAG) and long-context LLM (LCLM) approaches across three key dimensions: (1) the b",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "9f75697075e0f5691e3b821037b908c05f1821a7",
 "stated_evidence": "https://huggingface.co/datasets/VISAI-AI/nitibench/blob/9f75697075e0f5691e3b821037b908c05f1821a7/README.md",
 "file_evidence": "https://huggingface.co/datasets/VISAI-AI/nitibench/tree/9f75697075e0f5691e3b821037b908c05f1821a7",
 "card_nc": false
}