ClinAlign: Scaling Healthcare Alignment from Clinician Preference
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915790177959936 |
|---|---|
| author | Lyu, Shiwei Wang, Xidong Liu, Lei Zhu, Hao Zhang, Chaohe Wang, Jian Gu, Jinjie Wang, Benyou Shen, Yue |
| author_facet | Lyu, Shiwei Wang, Xidong Liu, Lei Zhu, Hao Zhang, Chaohe Wang, Jian Gu, Jinjie Wang, Benyou Shen, Yue |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09653 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ClinAlign: Scaling Healthcare Alignment from Clinician Preference Lyu, Shiwei Wang, Xidong Liu, Lei Zhu, Hao Zhang, Chaohe Wang, Jian Gu, Jinjie Wang, Benyou Shen, Yue Artificial Intelligence 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. |
| title | ClinAlign: Scaling Healthcare Alignment from Clinician Preference |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.09653 |