@inproceedings{sun-etal-2026-mentalseek,
    title = "{M}ental{S}eek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis",
    author = "Sun, Xiao  and
      Ymyang  and
      Jiang, Xinyi  and
      Tian, Yu  and
      Zhu, Junnan  and
      Zhong, Jiang  and
      Lei, Qin  and
      Huang, Jingwang  and
      Zeng, Haoyang  and
      Zhou, Xinyu  and
      Xiao, Xin  and
      Wei, Kaiwen",
    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.1225/",
    pages = "26600--26636",
    ISBN = "979-8-89176-390-6",
    abstract = "Mental health disorders represent a burgeoning global public health challenge. While Large Language Models (LLMs) have demonstrated potential in psychiatric assessment, their clinical utility is severely constrained by benchmarks that lack ecological validity and fine-grained diagnostic supervision. To bridge this gap, we introduce $\textbf{MentalDx Bench}$, the first benchmark dedicated to disorder-level psychiatric diagnosis within real-world clinical settings. Comprising 712 de-identified electronic health records annotated by board-certified psychiatrists under ICD-11 guidelines, the benchmark covers 76 disorders across 16 diagnostic categories. Evaluation of 18 LLMs reveals a critical $\textit{paradigm misalignment}$: strong performance at coarse diagnostic categorization contrasts with systematic failure at disorder-level diagnosis, underscoring a gap between pattern-based modeling and clinical hypothetico-deductive reasoning.In response, we propose $\textbf{MentalSeek-Dx}$, a medical-specialized LLM trained to internalize this clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning. Experiments on MentalDx Bench demonstrate that MentalSeek-Dx achieves state-of-the-art (SOTA) performance with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis. The dataset and code are available."
}