CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
arXiv:2609.38810v2 Announce Type: replace-cross Abstract: As vision language models are increasingly deployed in clinical diagnosis, under standing how they internally resolve competing visual and textual signals becomes a safety imperative. Existing mechanistic analyses remain confined to unimodal text and offer no explanation for why a single misleading sentence can override a correct image based diagnosis, or why a model commits to a confident answer despite insufficient visual evidence. We…