作者位次 #2/4ACL 2026Poster· Natural Language Processing
PAM : Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition
Zhihao Xu · Fuzhen Yang · Liang Lin · Xiting Wang
摘要
Recent advancements in Large Reasoning Models (LRMs) have showcased strong performance across various reasoning tasks by leveraging System-2 thinking capabilities. However, existing studies indicate that this reasoning ability alone does not reliably transfer to the general alignment domain. Insp...