{
 "id": "nlphuji/DOVE",
 "owner": "nlphuji",
 "name": "DOVE",
 "downloads": 59,
 "likes": 5,
 "last_modified": "2025-08-14T10:14:01.000Z",
 "stated_licence": "cdla-permissive-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "multiple-choice",
  "text-generation"
 ],
 "citation": "@inproceedings{habba-etal-2025-dove,\n    title = \"{DOVE}: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful {LLM} Evaluation\",\n    author = \"Habba, Eliya  and\n      Arviv, Ofir  and\n      Itzhak, Itay  and\n      Perlitz, Yotam  and\n      Bandel, Elron  and\n      Choshen, Leshem  and\n      Shmueli-Scheuer, Michal  and\n      Stanovsky, Gabriel\",\n    editor = \"Che, Wanxiang  and\n      Nabende, Joyce  and\n      Shutova, Ekaterina  and\n      Pilehvar, Mohammad Taher\",\n    booktitle = \"Findings of the Association for Computational Linguistics: ACL 2025\",\n    month = jul,\n    year = \"2025\",\n    address = \"Vienna, Austria\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.findings-acl.611/\",\n    doi = \"10.18653/v1/2025.findings-acl.611\",\n    pages = \"11744--11763\",\n    ISBN = \"979-8-89176-256-5\",\n    abstract = \"Recent work found that LLMs are sensitive to a wide range of arbitrary prompt dimensions, including the type of delimiters, answer enumerators, instruction wording, and more. This throws into question popular single-prompt evaluation practices. We present DOVE (Dataset Of Variation Evaluation) a large-scale dataset containing prompt perturbations of various evaluation benchmarks. In contrast to previous work, we examine LLM sensitivity from an holistic perspective, and assess the joint effects of perturbations along various dimensions, resulting in thousands of perturbations per instance. We evaluate se",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "b552dd99125a2d7b20a902c6e8fd303cf296b5a8",
 "stated_evidence": "https://huggingface.co/datasets/nlphuji/DOVE/blob/b552dd99125a2d7b20a902c6e8fd303cf296b5a8/README.md",
 "file_evidence": "https://huggingface.co/datasets/nlphuji/DOVE/tree/b552dd99125a2d7b20a902c6e8fd303cf296b5a8",
 "card_nc": false
}