构建首个印地语医学推理数据集，提升医疗大模型在印度医学中的表现
HiMed: Incentivizing Hindi Reasoning in Medical LLMs
- 设计渐退支架奖励机制，训练专用印地语医学推理模型
- 使印地语医学推理准确率显著提升，缩小与英语模型差距
- 涵盖西式与印度传统医学，适合关注本土化医疗AI的研究者
医疗大语言模型有望缓解医疗资源不均，但印地语仍严重缺乏支持。尽管医疗大模型在高资源语言中表现优异，其在印地语上的性能急剧下降，尤其在印度传统医学领域。我们认为，实现跨语言医疗迁移的关键在于印地语推理能力。为此，我们提出HiMed，一个覆盖西方与印度医学的印地语医学推理语料库与评测基准。进一步，我们通过渐退支架奖励机制设计出HiMed-8B，一种面向印地语的医学推理大模型。大量实验表明，该模型显著提升了印地语医学推理性能，并缩小了英语与印地语之间的准确率差距。消融实验验证了各训练阶段和奖励组件的有效性。所有数据与代码已公开于GitHub：https://github.com/FreedomIntelligence/HiMed。
原文摘要 · Abstract (English)
Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains severely underrepresented. While medical LLMs excel in high-resource languages, their performance degrades sharply in Hindi, particularly on Indian systems of medicine. We argue that robust cross-lingual medical transfer requires Hindi reasoning. To this end, we introduce HiMed, a Hindi reasoning medical corpus and benchmark suite covering both Western and Indian medicine. We further propose HiMed-8B, a Hindi-form medical reasoning LLM, through the design of decaying scaffolding reward. Extensive experiments demonstrate improvement in Hindi medical reasoning performance and reduction in the English--Hindi accuracy gap. Ablation studies validate the contribution of each training stage and reward component. All data and code are available on GitHub: https://github.com/FreedomIntelligence/HiMed.
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。