@inproceedings{ding-etal-2026-promed,
    title = "{P}ro{M}ed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical {LLM}s",
    author = "Ding, Hongxin  and
      Huang, Baixiang  and
      Fang, Yue  and
      Liao, Weibin  and
      Jiang, Xinke  and
      Zhang, Jinyang  and
      Zhu, Yinghao  and
      Li, Zheng  and
      Ma, Liantao  and
      Zhao, Junfeng  and
      Wang, Yasha",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1500/",
    pages = "32481--32515",
    ISBN = "979-8-89176-390-6",
    abstract = "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 details. To bridge this gap, we propose ProMed, a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making. Central to ProMed is the Shapley Information Gain (SIG) reward, which quantifies a question{'}s clinical utility as the amount of newly acquired information, while considering its contextual importance via Shapley values. We integrate SIG into a two-stage training pipeline: (1) SIG-Guided Model Initialization uses Monte Carlo Tree Search to construct high-reward interaction trajectories for supervision, and (2) SIG-Augmented Policy Optimization, with a novel SIG-guided Reward Distribution Mechanism that prioritizes informative questions for fine-grained optimization. Experiments on partial-information medical benchmarks show that ProMed significantly outperforms state-of-the-art methods by 6.29{\%} on average and delivers a 54.45{\%} gain over the reactive paradigm, and generalizes robustly to out-of-domain cases. Our codes are available at https://github.com/hxxding/ProMed."
}