作者位次 #2/11ACL 2026Poster· Natural Language Processing
P ro M ed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLM s
Hongxin Ding · Baixiang Huang · Yue Fang · Weibin Liao · Xinke Jiang · Jinyang Zhang · Yinghao Zhu · Zheng Li · Liantao Ma · Junfeng Zhao · Yasha Wang
摘要
Interactive medical questioning is essential in clinical consultations, where physicians must actively gather necessary patient information. Yet existing medical Large Language Models (LLMs) predominantly follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient...