用课程学习提升多语言医疗推理模型的准确与稳定
CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning
- 设计课程式强化学习框架，融合代码切换感知微调
- 13种语言下逻辑正确率最高达70.04%，语言一致性超94%
- 适合多语言医疗AI研发者，尤其关注公平性与可靠性
尽管大语言模型在单语数学和常识推理中表现良好，但在多语言医疗推理任务中仍不可靠，限制了其在多语言医疗场景中的应用。为此，我们首先构建了CUREMED-BENCH——一个高质量的多语言医疗推理数据集，包含13种语言的开放问答，涵盖阿姆哈拉语、约鲁巴语、斯瓦希里语等低资源语言。基于该数据集，提出CURE-MED框架，结合代码切换感知监督微调与组相对策略优化，协同提升逻辑正确性和语言稳定性。在13种语言上，该方法持续优于强基线，具有良好的可扩展性：70亿参数下实现54.35%逻辑正确率与85.21%语言一致性；320亿参数下达70.04%逻辑正确率与94.96%语言一致性。结果表明，该方法能支持可靠且公平的多语言医疗推理。代码与数据集已公开于https://cure-med.github.io/
原文摘要 · Abstract (English)
While large language models (LLMs) have shown to perform well on monolingual mathematical and commonsense reasoning, they remain unreliable for multilingual medical reasoning applications, hindering their deployment in multilingual healthcare settings. We address this by first introducing CUREMED-BENCH, a high-quality multilingual medical reasoning dataset with open-ended reasoning queries with a single verifiable answer, spanning thirteen languages, including underrepresented languages such as Amharic, Yoruba, and Swahili. Building on this dataset, we propose CURE-MED, a curriculum-informed reinforcement learning framework that integrates code-switching-aware supervised fine-tuning and Group Relative Policy Optimization to jointly improve logical correctness and language stability. Across thirteen languages, our approach consistently outperforms strong baselines and scales effectively, achieving 85.21% language consistency and 54.35% logical correctness at 7B parameters, and 94.96% language consistency and 70.04% logical correctness at 32B parameters. These results support reliable and equitable multilingual medical reasoning in LLMs. The code and dataset are available at https://cure-med.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。