When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models 事件

When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models arXiv:2603.23085v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing medical chain-of-thought (CoT) models lack explicit mechanisms to represent and enforce causal reasoning, leaving them vulnerable to spurious correlations and limiting their clinical reliability.