{
 "id": "miracl/nomiracl",
 "owner": "miracl",
 "name": "nomiracl",
 "downloads": 1588,
 "likes": 13,
 "last_modified": "2024-11-23T19:30:15.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "miracl/miracl",
   "licence": "apache-2.0",
   "found": true,
   "evidence": "https://huggingface.co/datasets/miracl/miracl/blob/5be20db9509754dadad47689368639fcec739c00/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{thakur-etal-2024-knowing,\n    title = \"{``}Knowing When You Don{'}t Know{''}: A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation\",\n    author = \"Thakur, Nandan  and\n      Bonifacio, Luiz  and\n      Zhang, Crystina  and\n      Ogundepo, Odunayo  and\n      Kamalloo, Ehsan  and\n      Alfonso-Hermelo, David  and\n      Li, Xiaoguang  and\n      Liu, Qun  and\n      Chen, Boxing  and\n      Rezagholizadeh, Mehdi  and\n      Lin, Jimmy\",\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.730\",\n    pages = \"12508--12526\",\n    abstract = \"Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. However, prior work lacks a comprehensive evaluation of different language families, making it challenging to evaluate LLM robustness against errors in external retrieved knowledge. To overcome this, we establish **NoMIRACL**, a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. NoMIRACL includes both a non-relevant and a relevant subset. Queries in the non-relevant subset contain passages judged",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "ecd08778d0426a5ca28ac99763b0c9ddc2c78e68",
 "stated_evidence": "https://huggingface.co/datasets/miracl/nomiracl/blob/ecd08778d0426a5ca28ac99763b0c9ddc2c78e68/README.md",
 "file_evidence": "https://huggingface.co/datasets/miracl/nomiracl/tree/ecd08778d0426a5ca28ac99763b0c9ddc2c78e68",
 "card_nc": false
}