Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
Keywords: Hallucination Benchamrk, Hallucination Evaluation Method, Medical Large Vision Language Model
Abstract: Large Vision Language Models (LVLMs) are increasingly integral to healthcare applications, including medical visual question answering and imaging report generation. While these models inherit the robust capabilities of foundational Large Language Models (LLMs), they also inherit susceptibility to hallucinations—a significant concern in high-stakes medical contexts where the margin for error is minimal. However, currently, there are no dedicated methods or benchmarks for hallucination detection and evaluation in the medical field. To bridge this gap, we introduce Med-HallMark, the first benchmark specifically designed for hallucination detection and evaluation within the medical multimodal domain. This benchmark provides multi-tasking hallucination support, multifaceted hallucination data, and hierarchical hallucination categorization. Furthermore, we propose the MediHall Score, a new medical evaluative metric designed to assess LVLMs' hallucinations through a hierarchical scoring system that considers the severity and type of hallucination, thereby enabling a granular assessment of potential clinical impacts. We also present MedihallDetector, a novel Medical LVLM engineered for precise hallucination detection, which employs multitask training for hallucination detection. Through extensive experimental evaluations, we establish baselines for popular LVLMs using our benchmark. The findings indicate that MediHall Score provides a more nuanced understanding of hallucination impacts compared to traditional metrics and demonstrate the enhanced performance of MedihallDetector. We hope this work can significantly improve the reliability of LVLMs in medical applications. All resources of this work have been released.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 3479
Loading