解剖区域引导的对比解码：一种用于缓解医学视觉-语言模型幻觉的即插即用策略
Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
AI总结：
本文提出了解剖区域引导的对比解码策略，通过区域特定指导缓解医学视觉-语言模型的幻觉问题，提升诊断准确性。
摘要：
医学视觉-语言模型（MedVLMs）在临床应用中展现出巨大潜力。然而，其可靠性受到幻觉的阻碍，其中模型往往无法从视觉证据中推导出答案，而是依赖于学习的文本先验。现有的缓解策略对于MedVLMs有显著的局限性：基于训练的方法依赖于昂贵的专家标注，限制了可扩展性，而基于训练的干预措施如对比解码，虽然数据效率高，但应用全球性的、无针对性的修正，在复杂的现实临床环境中效果不可靠。为了解决这些挑战，我们引入了解剖区域引导的对比解码（ARCD），一种即插即用的策略，通过提供有针对性的、区域特定的指导来缓解幻觉。我们的模块利用解剖学掩码来指导一个三级对比解码过程。通过在token、注意力和logits层面动态重新加权，它可验证地将模型的焦点引导到指定区域，加强解剖学理解并抑制事实性错误的输出。在多样化的数据集上进行了广泛的实验，包括胸部X光、CT、脑部MRI和眼底超声，证明了我们的方法在提高区域理解、减少幻觉和增强整体诊断准确性方面的有效性。
英文摘要：
Medical Vision-Language Models (MedVLMs) show immense promise in clinical applicability. However, their reliability is hindered by hallucinations, where models often fail to derive answers from visual evidence, instead relying on learned textual priors. Existing mitigation strategies for MedVLMs have distinct limitations: training-based methods rely on costly expert annotations, limiting scalability, while training-free interventions like contrastive decoding, though data-efficient, apply a global, untargeted correction whose effects in complex real-world clinical settings can be unreliable. To address these challenges, we introduce Anatomical Region-Guided Contrastive Decoding (ARCD), a plug-and-play strategy that mitigates hallucinations by providing targeted, region-specific guidance. Our module leverages an anatomical mask to direct a three-tiered contrastive decoding process. By dynamically re-weighting at the token, attention, and logits levels, it verifiably steers the model's focus onto specified regions, reinforcing anatomical understanding and suppressing factually incorrect outputs. Extensive experiments across diverse datasets, including chest X-ray, CT, brain MRI, and ocular ultrasound, demonstrate our method's effectiveness in improving regional understanding, reducing hallucinations, and enhancing overall diagnostic accuracy.
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。
