@inproceedings{deng-etal-2026-multidx,
    title = "{M}ulti{D}x: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning",
    author = "Deng, Yimin  and
      Lin, Zhenxi  and
      Wang, Yejing  and
      Zhao, Guoshuai  and
      Jia, Pengyue  and
      Fu, Zichuan  and
      Xu, Derong  and
      Zheng, Yefeng  and
      Zhao, Xiangyu  and
      Zhu, Li  and
      Wu, Xian  and
      Qian, Xueming",
    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.1646/",
    pages = "32904--32921",
    ISBN = "979-8-89176-395-1",
    abstract = "Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While large language models have shown strong capabilities in commonsense reasoning, they still struggle with diagnostic reasoning due to limited domain knowledge. Existing approaches often rely on internal model knowledge or static knowledge bases, which are insufficient to support the knowledge demands of diagnostic reasoning. Moreover, these methods focus solely on the accuracy of final predictions, overlooking alignment with standard clinical reasoning trajectories. To this end, we propose MultiDx, a two-stage diagnostic reasoning framework that performs differential diagnosis by analyzing evidence collected from multiple knowledge sources. Specifically, it first generates suspected diagnoses and reasoning traces by leveraging knowledge from web search, SOAP-formatted case, and clinical case database. Then it integrates multi-perspective evidence through matching, voting, and differential diagnosis to generate the final prediction. Extensive experiments demonstrate the effectiveness of our approach."
}