{
 "id": "ltg/noropenbookqa",
 "owner": "ltg",
 "name": "noropenbookqa",
 "downloads": 1291,
 "likes": 2,
 "last_modified": "2025-05-07T12:04:12.000Z",
 "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{mikhailov-etal-2025-collection,\n    title = \"A Collection of Question Answering Datasets for {Norwegian}\",\n    author = \"Mikhailov, Vladislav  and\n      M{\\ae}hlum, Petter  and\n      Lang{\\o}, Victoria Ovedie Chruickshank  and\n      Velldal, Erik  and\n      {\\O}vrelid, Lilja\",\n    editor = \"Johansson, Richard  and\n      Stymne, Sara\",\n    booktitle = \"Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)\",\n    month = mar,\n    year = \"2025\",\n    address = \"Tallinn, Estonia\",\n    publisher = \"University of Tartu Library\",\n    url = \"https://aclanthology.org/2025.nodalida-1.43/\",\n    pages = \"397--407\",\n    ISBN = \"978-9908-53-109-0\",\n    abstract = \"This paper introduces a new suite of question answering datasets for Norwegian; NorOpenBookQA, NorCommonSenseQA, NorTruthfulQA, and NRK-Quiz-QA. The data covers a wide range of skills and knowledge domains, including world knowledge, commonsense reasoning, truthfulness, and knowledge about Norway. Covering both of the written standards of Norwegian {--} Bokm{\\r{a}}l and Nynorsk {--} our datasets comprise over 10k question-answer pairs, created by native speakers. We detail our dataset creation approach and present the results of evaluating 11 language models (LMs) in zero- and few-shot regimes. Most LMs perform better in Bokm{\\r{a}}l than Nynorsk, struggle most with commonsense reasoning, and are often untruthf",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "b4712084a3d4610257cd3bfea53c4c5a582d9c9b",
 "stated_evidence": "https://huggingface.co/datasets/ltg/noropenbookqa/blob/b4712084a3d4610257cd3bfea53c4c5a582d9c9b/README.md",
 "file_evidence": "https://huggingface.co/datasets/ltg/noropenbookqa/tree/b4712084a3d4610257cd3bfea53c4c5a582d9c9b",
 "card_nc": false
}