arXiv:2601.18706 · v3

Health-SCORE: Improving Open-Ended Health LLMs Using Scalable Rubric-Based Rewards

首次提交 2026-01-27 01:34

版本更新 2026-11-01 03:40

雷达观测 2026-11-04 23:43

摘要

Reinforcement learning is a powerful approach for improving language models, but applying it to open-ended domains such as healthcare remains challenging because high-quality responses are often multidimensional, context-dependent, and difficult to capture with a single reward signal. Rubrics offer a natural form of supervision by providing a structured representation of the criteria that define a strong response. Existing rubric-based approaches, however, often rely on instance-specific criteria, creating two important limitations: (1) such rubrics are typically unavailable for unseen examples at test time; and (2) constructing new rubrics for every instance incurs substantial reward design costs. We introduce Health-SCORE, a scalable framework that captures recurring principles of response quality in the form of reusable meta-rubrics. Rather than relying on manually constructed instance-level criteria, Health-SCORE captures generalizable principles that can be applied across examples, tasks, and healthcare datasets. These meta-rubrics support two forms of model improvement: they can serve as structured, safety-aware reward signals for reinforcement learning during post-training, and they can be incorporated directly into prompts to guide model behavior at inference time. Across several open-ended healthcare benchmarks, models trained with Health-SCORE achieve performance competitive with models trained using human-authored instance-level rewards, while substantially reducing reward-design costs and improving generalizability.

作者备注：Published at EMNLP 2026 - Findings