{
 "id": "IDEA-AI4S/MoleculeQA",
 "owner": "IDEA-AI4S",
 "name": "MoleculeQA",
 "downloads": 464,
 "likes": 6,
 "last_modified": "2024-11-26T15:40:29.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering"
 ],
 "citation": "@inproceedings{lu-etal-2024-moleculeqa,\n    title = \"{M}olecule{QA}: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension\",\n    author = \"Lu, Xingyu  and\n      Cao, He  and\n      Liu, Zijing  and\n      Bai, Shengyuan  and\n      Chen, Leqing  and\n      Yao, Yuan  and\n      Zheng, Hai-Tao  and\n      Li, Yu\",\n    editor = \"Al-Onaizan, Yaser  and\n      Bansal, Mohit  and\n      Chen, Yun-Nung\",\n    booktitle = \"Findings of the Association for Computational Linguistics: EMNLP 2024\",\n    month = nov,\n    year = \"2024\",\n    address = \"Miami, Florida, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.findings-emnlp.216\",\n    pages = \"3769--3789\",\n    abstract = \"Large language models are playing an increasingly significant role in molecular research, yet existing models often generate erroneous information. Traditional evaluations fail to assess a model{'}s factual correctness. To rectify this absence, we present MoleculeQA, a novel question answering (QA) dataset which possesses 62K QA pairs over 23K molecules. Each QA pair, composed of a manual question, a positive option and three negative options, has consistent semantics with a molecular description from authoritative corpus. MoleculeQA is not only the first benchmark to evaluate molecular factual correctness but also the largest molecular QA dataset. A comprehensive evaluation on MoleculeQA for existing molecular LLMs exposes their deficiencies in specific as",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "cd1bcb922c9127b57e0944cdb605baccaa98ef9d",
 "stated_evidence": "https://huggingface.co/datasets/IDEA-AI4S/MoleculeQA/blob/cd1bcb922c9127b57e0944cdb605baccaa98ef9d/README.md",
 "file_evidence": "https://huggingface.co/datasets/IDEA-AI4S/MoleculeQA/tree/cd1bcb922c9127b57e0944cdb605baccaa98ef9d",
 "card_nc": false
}