@inproceedings{liang-etal-2026-medqpa,
    title = "{M}ed{QPA}-Gen: Medical Question Proposing and Answering for Report Generation",
    author = "Liang, Weijie  and
      Zhu, Xiyue  and
      Zhu, Ruike  and
      Li, Chenhao  and
      Tang, Cheng  and
      Liu, Zhiyu  and
      Gong, Zhihua  and
      Luo, Shirui  and
      Li, Yudu  and
      Kindratenko, Volodymyr",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.2139/",
    pages = "43120--43132",
    ISBN = "979-8-89176-395-1",
    abstract = "Medical report generation from medical images is a vital AI task that helps doctors with diagnosis and marks a significant step toward creating general AI-powered medical systems. However, previous methods either fail to optimize factual accuracy or heavily depend on expert preference data. To overcome these challenges, we propose {MedQPA}, an automatic and generalizable report evaluation technique that uses question proposing and answering to enable controllable, structured reasoning grounded in medical domain knowledge and the factual correctness of the report. Additionally, we design {MedQPA-Gen}, a medical report generation pipeline that maximizes the {MedQPA} score through prompt engineering and reinforcement learning with {MedQPA} as a reward signal. We demonstrate that {MedQPA} is an accurate evaluation metric that closely correlates with human preferences. More importantly, {MedQPA-Gen} achieves higher human preference scores and better performance on downstream tasks. We open-source code at this repo https://github.com/MedQPA-gen/MedQPA-gen."
}