用专业小模型协作解决医疗问答难题，本地部署更安全。
SOLVE-Med: Specialized Orchestration for Leading Vertical Experts across Medical Specialties
- 分领域小模型+智能调度器，动态匹配专家
- 在10个专科上达到ROUGE-1 0.301、BERTScore 0.697
- 比14B大模型还强，适合医院本地部署
医疗问答系统面临幻觉、偏见、计算开销、隐私问题及跨领域专业性挑战。本文提出SOLVE-Med，一种多智能体架构，融合多个领域专用的小型语言模型应对复杂医疗问题。系统包含一个路由代理（Router Agent）用于动态选择专家，十个各具10亿参数的专用模型（在特定医学领域微调），以及一个合成代理（Orchestrator Agent）整合答案。在涵盖十大学科的意大利医疗论坛数据集上评估，SOLVE-Med在ROUGE-1上达0.301，在BERTScore F1上达0.697，性能优于参数高达140亿的独立模型，同时支持本地化部署。代码已开源：https://github.com/PRAISELab-PicusLab/SOLVE-Med。
原文摘要 · Abstract (English)
Medical question answering systems face deployment challenges including hallucinations, bias, computational demands, privacy concerns, and the need for specialized expertise across diverse domains. Here, we present SOLVE-Med, a multi-agent architecture combining domain-specialized small language models for complex medical queries. The system employs a Router Agent for dynamic specialist selection, ten specialized models (1B parameters each) fine-tuned on specific medical domains, and an Orchestrator Agent that synthesizes responses. Evaluated on Italian medical forum data across ten specialties, SOLVE-Med achieves superior performance with ROUGE-1 of 0.301 and BERTScore F1 of 0.697, outperforming standalone models up to 14B parameters while enabling local deployment. Our code is publicly available on GitHub: https://github.com/PRAISELab-PicusLab/SOLVE-Med.
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。