在大型视觉语言模型中检测和评估医学幻觉
Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
AI总结：
本文提出Med-HallMark基准，用于医疗多模态领域中的幻觉检测与评估，引入MediHall Score和MediHallDetector，通过多任务训练提升模型可靠性，实验表明其在医疗应用中更有效。
摘要：
大型视觉语言模型（LVLMs）在医疗应用中日益重要，包括医学视觉问答和影像报告生成。尽管这些模型继承了基础大语言模型（LLMs）的鲁棒性，但也继承了幻觉的易感性，这在高风险医疗领域尤为严重。然而，目前尚无专门用于医疗领域幻觉检测和评估的方法或基准。为此，我们引入Med-HallMark，首个专门设计用于医疗多模态领域幻觉检测与评估的基准。该基准提供多任务幻觉支持、多维幻觉数据和分层幻觉分类。此外，我们提出了MediHall Score，一种新的医疗评估指标，通过分层评分系统评估LVLMs的幻觉，考虑幻觉的严重性和类型，从而实现对潜在临床影响的细致评估。我们还提出了MediHallDetector，一种新的医疗LVLM，用于精确的幻觉检测，采用多任务训练进行幻觉检测。通过广泛的实验评估，我们利用我们的基准建立了流行LVLMs的基线。研究结果表明，MediHall Score相比传统指标提供了更细致的幻觉影响理解，并展示了MediHallDetector的增强性能。我们希望这项工作能显著提高LVLMs在医疗应用中的可靠性。所有资源已发布在https://github.com/ydk122024/Med-HallMark。
英文摘要：
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 at https://github.com/ydk122024/Med-HallMark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
