@inproceedings{lyu-etal-2026-clinalign,
    title = "{C}lin{A}lign: Scaling Healthcare Alignment from Clinician Preference",
    author = "Lyu, Shiwei  and
      Wang, Xidong  and
      Zhu, Hao  and
      Liu, Lei  and
      Zhang, Chaohe  and
      Wang, Jian  and
      Gu, Jinjie  and
      Wang, Benyou  and
      Shen, Yue",
    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.825/",
    pages = "16727--16747",
    ISBN = "979-8-89176-395-1",
    abstract = "Although large language models (LLMs) demonstrate expert-level medical knowledge, aligning their open-ended outputs with fine-grained clinician preferences remains challenging. Existing methods often rely on coarse objectives or unreliable automated judges that are weakly grounded in professional guidelines. We propose a two-stage framework to address this gap. First, we introduce HealthRubrics, a dataset of 7,034 physician-verified preference examples in which clinicians refine LLM-drafted rubrics to meet rigorous medical standards. Second, we distill these rubrics into HealthPrinciples: 119 broadly reusable, clinically grounded principles organized by clinical dimensions, enabling scalable supervision beyond manual annotation. We use HealthPrinciples for (1) offline alignment by synthesizing rubrics for unlabeled queries and (2) an inference-time tool for guided self-revision. A 30A3B model with our framework achieves 33.4{\%} on HealthBench-Hard, outperforming much larger models including Deepseek-R1 and o3, establishing a resource-efficient baseline for clinical alignment."
}