This work introduces MedJudge, a multimodal medical reward modeling method that supports interpretable, evidence-grounded, and clinically-aligned decision evaluation, and proposes UMLS-based Concept Overlap (UCO) to evaluate explanation quality, measuring concept-level alignment with clinician expectations.
Yun-Hong He, Kai Zhang, Jiarong Qian et al.· Proceedings of the 32nd ACM...· 0 citations
CMPM, a Chinese Multi-Panel Meme benchmark with 1,214 annotated samples covering five structural types, ordering dependency, panel-order constraints, and optional comment context, is introduced and results indicate that canonical-display accuracy is not by itself evidence of order understanding.
Haihan Li, Hai-Hao Li, Zheng-Jie Xu et al.· 0 citations
This work introduces MedJudge, a multimodal medical reward modeling method that supports interpretable, evidence-grounded, and clinically-aligned decision evaluation, and proposes UMLS-based Concept Overlap (UCO) to evaluate explanation quality, measuring concept-level alignment with clinician expectations.
Yunhong He, Kai Zhang, Jiarong Qian et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
