MedCausalX: Adaptive Causal Reasoning with Self-Reflection for Trustworthy Medical Vision-Language Models

ArXi:2603.23085v1 Announce Type: new 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.