作者位次 #7/11ACL 2026Poster· Natural Language Processing
C heck RLM : Effective Knowledge–Thought Coherence Checking in Retrieval-Augmented Reasoning
Dingling Xu · Ruobing Wang · Qingfei Zhao · Yukun Yan · Zhichun Wang · Daren Zha · Shi Yu · Zhenghao Liu · Shuo Wang · Xu Han · Maosong Sun
摘要
Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual errors, particularly in knowledge-intensive tasks. To address this issue, we propose CheckRLM , a framework that improv...