# 基于知识增强数据合成与半监督强化学习的医学推理激发方法

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-13 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmnygovrm003osl136kt9dtsk
- 原文链接：https://arxiv.org/abs/2604.11547

## AI 摘要

MedSSR 框架通过知识增强数据合成与半监督强化学习提升医学推理能力。该方法利用罕见疾病知识合成分布可控的推理问题，并基于策略模型生成伪标签，实现"自监督 RL+监督 RL"的两阶段训练，无需依赖昂贵的推理痕迹蒸馏。在 Qwen 和 LLaMA 上的实验表明，该方法在十个医疗基准测试中均优于现有方法，在罕见病任务上准确率提升高达 5.93%。

## 正文

While large language models hold promise for complex medical applications, their development is hindered by the scarcity of high-quality reasoning data. To address this issue, existing approaches typically distill chain-of-thought reasoning traces from large proprietary models via supervised fine-tuning, then conduct reinforcement learning (RL). These methods exhibit limited improvement on underrepresented domains like rare diseases while incurring substantial costs from generating complex reasoning chains. To efficiently enhance medical reasoning, we propose MedSSR, a Medical Knowledge-enhanced data Synthesis and Semi-supervised Reinforcement learning framework. Our framework first employs rare disease knowledge to synthesize distribution-controllable reasoning questions. We then utilize the policy model itself to generate high-quality pseudo-labels. This enables a two-stage, intrinsic-to-extrinsic training paradigm: self-supervised RL on the pseudo-labeled synthetic data, followed by supervised RL on the human-annotated real data. MedSSR scales model training efficiently without relying on costly trace distillation. Extensive experiments on Qwen and Llama demonstrate that our method outperforms existing methods across ten medical benchmarks, achieving up to +5.93% gain on rare-disease tasks. Our code is available at https://github.com/tdlhl/MedSSR.