作者位次 #4/5ACL 2026Poster· Natural Language Processing
CLAR ity: Reasoning Consistency Alone Can Teach Reinforced Experts
Jiuheng Lin · Cong Jiang · Zirui Wu · Jiarui Sun · Yansong Feng
摘要
Training expert LLMs in domains with scarce fine-grained annotated data is admittedly challenging, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While outcome-based RL may improve accuracy, it frequently compromise...