一作ACL 2026Poster· Natural Language Processing
Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards
Raffaele Pisano · Roberto Navigli
摘要
Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (LLMs), which frequently produce chains of thought (CoTs) containing errors even when the final answer is correct. However, existing PRM datasets r...