作者位次 #3/12ACL 2026Poster· Natural Language Processing
LANG : Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
Yuchun Fan · Bei Li · Peiguang Li · Yilin Wang · Yongyu Mu · Jian Yang · Xin Chen · Rongxiang Weng · Jingang Wang · Xunliang Cai · JingBo Zhu · Tong Xiao
摘要
Reinforcement learning has proven effective for enhancing multi-step reasoning in Large Language Models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off: prioritizing input-language consistency severely hampers rea...