ClinAlign：基于临床医生偏好的医疗决策协同扩展框架

摘要

尽管大型语言模型（LLMs）展现出专家级的医学知识储备，但将其开放式输出与临床医生细粒度的偏好对齐仍具挑战。现有方法通常依赖粗粒度的优化目标或基于专业指南关联性弱的不可靠自动评估器。为此，我们提出一个两阶段框架：首先发布HealthRubrics数据集，包含7,034个经医师验证的偏好样本，临床医生通过优化LLM起草的评估细则以符合严格医疗标准；其次将这些细则提炼为HealthPrinciples——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。我们运用HealthPrinciples实现（1）通过为未标注查询生成细则进行离线对齐，（2）作为推理时引导自我修正的工具。采用本框架训练的参数量300亿、推理时仅激活30亿参数的模型，在HealthBench-Hard基准上达到33.4%的准确率，超越包括Deepseek-R1和o3在内的更大模型，为临床对齐任务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.

ClinAlign：基于临床医生偏好的医疗决策协同扩展框架

ClinAlign: Scaling Healthcare Alignment from Clinician Preference

摘要

Support