{
 "id": "dtk-llms/XSTest",
 "owner": "dtk-llms",
 "name": "XSTest",
 "downloads": 5,
 "likes": 0,
 "last_modified": "2025-11-10T14:22:58.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{rottger-etal-2024-xstest,\n    title = \"{XST}est: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models\",\n    author = {R{\\\"o}ttger, Paul  and\n      Kirk, Hannah  and\n      Vidgen, Bertie  and\n      Attanasio, Giuseppe  and\n      Bianchi, Federico  and\n      Hovy, Dirk},\n    editor = \"Duh, Kevin  and\n      Gomez, Helena  and\n      Bethard, Steven\",\n    booktitle = \"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)\",\n    month = jun,\n    year = \"2024\",\n    address = \"Mexico City, Mexico\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.naacl-long.301/\",\n    doi = \"10.18653/v1/2024.naacl-long.301\",\n    pages = \"5377--5400\",\n    abstract = \"Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both helpful and harmless. However, there is a tension between these two objectives, since harmlessness requires models to refuse to comply with unsafe prompts, and thus not be helpful. Recent anecdotal evidence suggests that some models may have struck a poor balance, so that even clearly safe prompts are refused if they use similar language to unsafe prompts or mention sensitive topics. In this pape",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "03dd5f6f14f758074d7a00dc563836958d390dae",
 "stated_evidence": "https://huggingface.co/datasets/dtk-llms/XSTest/blob/03dd5f6f14f758074d7a00dc563836958d390dae/README.md",
 "file_evidence": "https://huggingface.co/datasets/dtk-llms/XSTest/tree/03dd5f6f14f758074d7a00dc563836958d390dae",
 "card_nc": false
}