作者位次 #4/8ACL 2026Poster· Natural Language Processing
Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
Xue Zhang · Yunlong Liang · Fandong Meng · Songming Zhang · Kaiyu Huang · Yufeng Chen · Xu Jinan · Jie Zhou
摘要
Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the “think-then-answer” paradigm, which enhances both accuracy and interpretability. However, current LRMs exhibit two critical limitations when processing non-English languages: (1) They oft...