ClinAlign: Scaling Healthcare Alignment from Clinician Preference
This addresses the problem of unreliable medical outputs from AI for clinicians, though it is incremental as it builds on existing alignment methods.
The paper tackled the challenge of aligning large language models with fine-grained clinician preferences in healthcare by introducing a two-stage framework that includes a physician-verified dataset and distilled principles, resulting in a 30B-A3B model achieving 33.4% on HealthBench-Hard and outperforming larger models.
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-A3B model 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.