作者位次 #4/11ACL 2026Poster· Natural Language Processing
Q uantum QA : Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning
Songxin Qu · Tai-Ping Sun · Yun-Jie Wang · Huan-Yu Liu · Cheng Xue · Xiao-Fan Xu · Han Fang · Yang Yang · Yu-Chun Wu · Guo-Ping Guo · Zhao-Yun Chen
摘要
Large language models (LLMs) show strong capabilities in general reasoning but typically lack reliability in scientific domains like quantum mechanics, which demand strict adherence to physical constraints. This limitation arises from the scarcity of verifiable training resources and the inadequa...