用渐进式训练让医疗大模型更懂专业，效果优于现有方法
Generalization of Medical Large Language Models through Cross-Domain Weak Supervision
- 分阶段训练，逐步从通用语言过渡到医学专精
- 在问答、生成等任务上准确率与效率双提升
- 适合需要可靠医疗生成的临床辅助系统
大型语言模型的发展为自然语言处理带来了新突破，尤其在医疗等专业领域。本文提出增量式课程微调（ICFT）框架，通过课程学习、双阶段记忆协同与参数高效微调，实现从通用语言知识到强医学专长的渐进式过渡。在多项医疗NLP任务（包括问答、偏好分类、响应生成）上的实验表明，ICFT持续优于当前最优基线，显著提升准确率与效率。进一步分析显示，该框架具备良好泛化能力，能减少错误并生成多样且上下文相关的医学响应。这些结果确立了ICFT作为适配医疗大模型的鲁棒且可扩展方案，具有实际医疗应用价值。
原文摘要 · Abstract (English)
The advancement of large language models (LLMs) has opened new frontiers in natural language processing, particularly in specialized domains like healthcare. In this paper, we propose the Incremental Curriculum-Based Fine-Tuning (ICFT) framework to enhance the generative capabilities of medical large language models (MLLMs). ICFT combines curriculum-based learning, dual-stage memory coordination, and parameter-efficient fine-tuning to enable a progressive transition from general linguistic knowledge to strong domain-specific expertise. Experimental results across diverse medical NLP tasks, including question answering, preference classification, and response generation, demonstrate that ICFT consistently outperforms state-of-the-art baselines, achieving improvements in both accuracy and efficiency. Further analysis reveals the framework's ability to generalize to unseen data, reduce errors, and deliver diverse, contextually relevant medical responses. These findings establish ICFT as a robust and scalable solution for adapting LLMs to the medical domain, offering practical benefits for real-world healthcare applications.
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。