基于反事实证据验证的医学视觉语言模型幻觉检测与纠正
Hallucination Detection and Correction in Medical VLMs via Counter-Evidence Verification
AI总结：
提出CoEV框架，通过文本与视觉证据的双向验证检测并纠正医学VLM幻觉，无需重新训练，在四个数据集上显著提升检测和纠正性能。
摘要：
视觉语言模型（VLM）在医学诊断中的可靠性受到幻觉的挑战，这削弱了信任。现有的幻觉检测方法主要关注识别生成文本与参考数据之间的事实不一致性。虽然一些研究分析了模型在图像中的注意力区域，但它们很少验证这种注意力是否真正反映了支持生成文本的视觉证据。为了解决这一差距，我们提出了反事实证据验证（CoEV），一个无需训练的即插即用框架，通过基于证据的事实一致性验证来检测和纠正幻觉。CoEV在文本断言和视觉证据之间执行双向验证，测试每个陈述是否得到其对应证据区域的支持，并将每个陈述分配到一个四象限诊断图中，该图捕获文本事实性和视觉基础性的组合。CoEV检测幻觉内容，并作为事后细化工具，无需重新训练即可纠正幻觉。在四个医学数据集上的大量实验表明，CoEV能够对抗幻觉。在幻觉检测方面，CoEV始终优于现有方法，平均PR-AUC和ROC-AUC分别提高了3.0%和3.9%的绝对百分点，在特定VQA场景中提升高达18.5%。在幻觉纠正方面，它将Micro-F1提高了高达12.5%，在医学报告生成中将幻觉率降低了超过11.9%，并提高了医学VQA的准确性。这些结果表明，CoEV能够可靠地检测和纠正幻觉，为临床医生提供可靠的、基于证据的诊断线索。代码将在接收后发布。
英文摘要：
Vision-Language models (VLMs) reliability in medical diagnosis is challenged by trust-undermining hallucinations. Existing hallucination detection approaches mainly focus on identifying factual inconsistencies between generated text and reference data. While some studies analyze where models attend in images, they seldom verify whether such attention truly reflects the visual evidence supporting the generated text. To address this gap, we propose Co}unter-Evidence Verification (CoEV), a training-free plug-and-play framework that detects and corrects hallucinations through evidence-based factual consistency verification. CoEV performs bidirectional verification between textual assertions and visual evidence, testing whether each statement is supported by its corresponding evidence region, and assigns each statement into a four-quadrant diagnostic map capturing combinations of text factuality and visual grounding. CoEV detects hallucinated content and serves as a post hoc refinement tool, correcting hallucinations without retraining. Extensive experiments on four medical datasets show that CoEV combats hallucinations in VLMs.For hallucination detection, CoEV consistently outperforms existing methods, improving average PR-AUC and ROC-AUC by 3.0% and 3.9% absolute points respectively, with notable gains of up to 18.5% in specific VQA scenarios. For hallucination correction, it improves Micro-F1 by up to 12.5%, reduces hallucination rates by over 11.9% on medical report generation, and also boosts medical VQA accuracy. These results show that CoEV enables reliable detection and correction of hallucinations, providing clinicians with dependable, evidence-based cues for diagnosis. Code will be released upon acceptance.
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。
