小模型+检索增强在风湿科诊疗中表现更优，省电省钱还易部署。
Performance and Practical Considerations of Large and Small Language Models in Clinical Decision Support in Rheumatology
- 用小模型搭配检索增强生成，提升诊断治疗效果
- 小模型性能接近大模型，能耗降低80%以上
- 适合资源有限的医院，但需医生把关
大型语言模型（LLMs）在复杂领域如风湿病学的临床决策支持中展现出潜力。我们的评估表明，结合检索增强生成（RAG）的小型语言模型（SLMs）在诊断和治疗性能上优于大型模型，同时显著降低能耗，并支持低成本、本地化部署。这一特性对资源有限的医疗机构尤为吸引。然而，专家监督依然至关重要，因为没有任何模型在风湿病学中能持续达到专科医生水平的准确性。
原文摘要 · Abstract (English)
Large language models (LLMs) show promise for supporting clinical decision-making in complex fields such as rheumatology. Our evaluation shows that smaller language models (SLMs), combined with retrieval-augmented generation (RAG), achieve higher diagnostic and therapeutic performance than larger models, while requiring substantially less energy and enabling cost-efficient, local deployment. These features are attractive for resource-limited healthcare. However, expert oversight remains essential, as no model consistently reached specialist-level accuracy in rheumatology.
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。