MedHal：用于医疗幻觉检测的大规模合成数据集

View PDF HTML (experimental)

Abstract:Hallucination, the generation of non factual content by AI systems, poses serious risks in medical contexts, where errors can directly affect patient outcomes. We present MedHal, a large-scale dataset specifically designed to assess capabilities and train models on the task of hallucination detection in medical texts. Current hallucination detection methods face significant limitations when applied to specialized domains like medicine, where they can have disastrous consequences. MedHal addresses this issue by incorporating diverse medical text sources and tasks covering both intrinsic and extrinsic hallucinations, and by providing a substantial volume of data samples suitable for training medical hallucination detection models. We demonstrate MedHal's utility by training and evaluating a baseline medical hallucination detection model, showing improvements over general-purpose hallucination detection approaches. This resource enables more efficient evaluation and training of medical text generation systems while reducing reliance on costly expert review, potentially accelerating the development of medical AI research.

Comments:	The 5th Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing, November 6-10, 2026, Hengqin, China
Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
ACM classes:	I.2.7
Cite as:	arXiv:2504.08596 [cs.CL]
	(or arXiv:2504.08596v4 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2504.08596 arXiv-issued DOI via DataCite

Submission history

From: Gaya Mehenni [view email]
[v1] Fri, 11 Apr 2025 14:55:15 UTC (243 KB)
[v2] Tue, 7 Oct 2025 15:40:54 UTC (189 KB)
[v3] Fri, 25 Sep 2026 01:33:25 UTC (58 KB)
[v4] Tue, 20 Oct 2026 00:20:06 UTC (58 KB)