针对医学视觉-语言模型中否定处理改进的分层微调
NAST: Improving Negation Handling in Medical Vision-Language Models through Negation-Aware Selective Training
AI总结：
本研究提出NAST方法，通过因果追溯效应调节逐层梯度更新，提升医学视觉-语言模型对否定处理的识别能力，同时保持一般视觉-语言对齐。
摘要：
否定是临床报告中的基本语言操作，然而视觉-语言模型（VLMs）经常无法区分肯定和否定的医学陈述。为了系统地表征这一局限性，我们引入了一个专门针对放射学的诊断基准，评估在受控临床条件下极性敏感性，揭示了常见医学VLMs在混淆否定和非否定发现方面的一致性。为了使学习超越简单的条件缺失，我们进一步构建了一个上下文临床否定数据集，该数据集编码了结构化的声明，并支持涉及位置和严重程度的属性级否定。基于这些资源，我们提出了Negation-Aware Selective Training（NAST），一种基于可解释性指导的适应方法，利用因果追溯效应（CTEs）在微调过程中调节逐层梯度更新。而不是应用统一的学习率，NAST根据每层对否定处理的因果贡献来调整每个层的更新，将机制性可解释性信号转化为一种原则性的优化规则。实验表明，在不损害一般视觉-语言对齐的情况下，改进了对肯定和否定临床陈述的辨别能力，突显了因果可解释性在安全关键医疗环境中的适应价值。代码和资源可在https://github.com/healthylaife/NAST获取。
英文摘要：
Negation is a fundamental linguistic operation in clinical reporting, yet vision-language models (VLMs) frequently fail to distinguish affirmative from negated medical statements. To systematically characterize this limitation, we introduce a radiology-specific diagnostic benchmark that evaluates polarity sensitivity under controlled clinical conditions, revealing that common medical VLMs consistently confuse negated and non-negated findings. To enable learning beyond simple condition absence, we further construct a contextual clinical negation dataset that encodes structured claims and supports attribute-level negations involving location and severity. Building on these resources, we propose Negation-Aware Selective Training (NAST), an interpretability-guided adaptation method that uses causal tracing effects (CTEs) to modulate layer-wise gradient updates during fine-tuning. Rather than applying uniform learning rates, NAST scales each layer's update according to its causal contribution to negation processing, transforming mechanistic interpretability signals into a principled optimization rule. Experiments demonstrate improved discrimination of affirmative and negated clinical statements without degrading general vision-language alignment, highlighting the value of causal interpretability for targeted model adaptation in safety-critical medical settings. Code and resources are available at https://github.com/healthylaife/NAST.
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。
