LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models
LSR-Ben is introduced, a process-level benchmark specifically designed for assessing PRM's performance across two primary reasoning domains (scientific and logical reasoning) and nine subdomains and it is hoped LSR-Ben can foster future researches on PRMs for broader domains, thereby enhancing the reasoning capabilitie...
Zhouhao Sun, Xuan Zhang, Xiaofeng Ding et al.
· 0 citations