Trustworthy AI

CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
Causal tracing and targeted intervention for arbitration and brake failures in medical vision language models.
Chunzheng Zhu, Jiaqi Zeng, Hongbo Zhao, Yihang Chen, Yijun Wang, Jianxin Lin
CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
Trustworthy Medical Concept Recalibration through Logic-Aware Multimodal Evidence Fusion
ConChecker autonomously recalibrates medical concepts through logic-aware multimodal evidence fusion and verifiable policy optimization.
Lei Zhao, Chunzheng Zhu†, Zhan Gao, Pengchen Liang, Xiaoyun Liang, Alex Chit-Yuen Cheng, Chi-Man Pun
Trustworthy Medical Concept Recalibration through Logic-Aware Multimodal Evidence Fusion
When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models
Adaptive causal reasoning with self-reflection for trustworthy medical vision-language models.
Jianxin Lin†, Chunzheng Zhu†, Peter J. Kneuertz, Yunfei Bai, Yuan Xue
When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models