MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning
MedPRMBench is introduced, a step-level medical reasoning benchmark with 14 clinical error types, including five new and two clinically re-scoped types, and rule-defined severity grades, and the training signal replicates across model families.
Ling-Yan Wu, Xiang-Xiang Zheng, Wei-Qi Zhai et al.
· arXiv.org · 2 citations