CURE-MED：基于课程的强化学习用于多语言医学推理
CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning
AI总结：
本文提出CURE-MED框架，通过课程引导的强化学习提升多语言医学推理的逻辑正确性和语言稳定性，实验表明在13种语言上均优于基线模型，实现了高一致性与高正确率。
摘要：
尽管大型语言模型在单语数学和常识推理中表现优异，但在多语言医学推理应用中仍不可靠，阻碍了其在多语言医疗环境中的部署。我们通过引入CUREMED-BENCH，一个高质量的多语言医学推理数据集，涵盖十三种语言，包括较少被代表的语言，如阿姆哈拉语、约鲁巴语和斯瓦希里语。基于此数据集，我们提出CURE-MED，一种课程引导的强化学习框架，整合了代码切换感知的监督微调和组相对策略优化，以共同提升逻辑正确性和语言稳定性。在十三种语言中，我们的方法在7B参数下达到85.21%的语言一致性和54.35%的逻辑正确率，在32B参数下达到94.96%的语言一致性和70.04%的逻辑正确率。这些结果支持了在LLM中实现可靠和公平的多语言医学推理。代码和数据集可在https://cure-med.github.io/获取。
英文摘要：
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/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
