ClinAlign：基于临床医生偏好的医疗决策协同规模化框架

ClinAlign: Scaling Healthcare Alignment from Clinician Preference

February 10, 2026

作者: Shiwei Lyu, Xidong Wang, Lei Liu, Hao Zhu, Chaohe Zhang, Jian Wang, Jinjie Gu, Benyou Wang, Yue Shen

cs.AI

摘要

尽管大语言模型展现出专家级的医学知识，但其开放式输出与临床医生细粒度偏好的对齐仍具挑战。现有方法常依赖粗粒度目标或基于专业指南关联性较弱的不可靠自动评估器。我们提出一个两阶段框架以解决这一差距：首先推出HealthRubrics数据集，包含7,034例经医师验证的偏好样本，临床医生通过优化LLM起草的评估细则以满足严格医疗标准；其次将这些细则提炼为HealthPrinciples——一套按临床维度组织的119条可复用临床原则，实现超越人工标注的可扩展监督。该框架将HealthPrinciples应用于（1）通过为未标注查询合成评估细则进行离线对齐，（2）作为推理时引导自我修正的工具。采用本框架训练的30B参数模型（推理时仅激活3B参数）在HealthBench-Hard基准上达到33.4%的得分，优于包括Deepseek-R1和o3在内的更大模型，为临床对齐建立了资源高效的基线。

English

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 30B parameter model that activates only 3B parameters at inference trained 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.