{
 "id": "GuardrailsAI/hallucination",
 "owner": "GuardrailsAI",
 "name": "hallucination",
 "downloads": 35,
 "likes": 2,
 "last_modified": "2025-02-12T02:02:47.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{ma-etal-2023-bump,\n    title = \"{BUMP}: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics\",\n    author = \"Ma, Liang  and\n      Cao, Shuyang  and\n      Logan IV, Robert L  and\n      Lu, Di  and\n      Ran, Shihao  and\n      Zhang, Ke  and\n      Tetreault, Joel  and\n      Jaimes, Alejandro\",\n    booktitle = \"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2023\",\n    address = \"Toronto, Canada\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.acl-long.716\",\n    pages = \"12788--12812\",\n    abstract = \"The proliferation of automatic faithfulness metrics for summarization has produced a need for benchmarks to evaluate them. While existing benchmarks measure the correlation with human judgements of faithfulness on model-generated summaries, they are insufficient for diagnosing whether metrics are: 1) consistent, i.e., indicate lower faithfulness as errors are introduced into a summary, 2) effective on human-written texts, and 3) sensitive to different error types (as summaries can contain multiple errors). To address these needs, we present a benchmark of unfaithful minimal pairs (BUMP), a dataset of 889 human-written, minimally different summary pairs, where a single error is introduced to a summary from the CNN/DailyMail dataset to produce an unfaithful summary. We find BUMP complements ",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "a2e98a97fca4134d4d79340fa6a7684e06a591c6",
 "stated_evidence": "https://huggingface.co/datasets/GuardrailsAI/hallucination/blob/a2e98a97fca4134d4d79340fa6a7684e06a591c6/README.md",
 "file_evidence": "https://huggingface.co/datasets/GuardrailsAI/hallucination/tree/a2e98a97fca4134d4d79340fa6a7684e06a591c6",
 "card_nc": false
}