arXiv 2512.058632025-12-05cs.CLcs.AI

优化医疗问答系统：基于RAG框架的微调与零样本大语言模型比较研究

Optimizing Medical Question-Answering Systems: A Comparative Study of Fine-Tuned and Zero-Shot Large Language Models with RAG Framework

Department of Electrical Engineering；Computer Science University of Toledo Toledo, USA；Institute of Mathematical Sciences Claremont Graduate University Claremont, USA；Department of Bioengineering University of Toledo Toledo, USA；Department of Computer Science Bowling Green State University Bowling Green, USA

Tasnimul Hassan, Md Faisal Karim, Haziq Jeelani, Elham Behnam, Robert Green, Fayeq Jeelani Syed

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文通过RAG框架结合微调与零样本大语言模型，提升医疗问答系统的准确性与可靠性，实验证明检索增强显著提高回答质量。

摘要：

医疗问答系统可以从大语言模型（LLMs）的进步中受益，但直接将LLMs应用于临床领域会面临保持事实准确性以及避免幻觉等挑战。本文提出了一种基于检索增强生成（RAG）的医疗问答系统，结合领域特定知识检索与开源LLMs来回答医疗问题。我们使用低秩适应（LoRA）对两种最先进的开源LLMs（LLaMA~2和Falcon）进行微调，以实现高效的领域专业化。系统通过检索相关医学文献来支撑LLM的回答，从而提高事实准确性并减少幻觉。我们在基准数据集（PubMedQA和MedMCQA）上评估了该方法，并显示检索增强在回答准确性方面相比仅使用LLMs有可测量的改进。我们的微调LLaMA~2模型在PubMedQA上达到了71.8%的准确率，显著优于55.4%的零样本基准，同时通过提供来源参考保持透明性。我们还详细说明了系统设计和微调方法，证明通过检索证据支撑答案可减少约60%的不支持内容。这些结果突显了RAG增强的开源LLMs在可靠生物医学问答中的潜力，指向实际的临床信息学应用。

英文摘要：

Medical question-answering (QA) systems can benefit from advances in large language models (LLMs), but directly applying LLMs to the clinical domain poses challenges such as maintaining factual accuracy and avoiding hallucinations. In this paper, we present a retrieval-augmented generation (RAG) based medical QA system that combines domain-specific knowledge retrieval with open-source LLMs to answer medical questions. We fine-tune two state-of-the-art open LLMs (LLaMA~2 and Falcon) using Low-Rank Adaptation (LoRA) for efficient domain specialization. The system retrieves relevant medical literature to ground the LLM's answers, thereby improving factual correctness and reducing hallucinations. We evaluate the approach on benchmark datasets (PubMedQA and MedMCQA) and show that retrieval augmentation yields measurable improvements in answer accuracy compared to using LLMs alone. Our fine-tuned LLaMA~2 model achieves 71.8% accuracy on PubMedQA, substantially improving over the 55.4% zero-shot baseline, while maintaining transparency by providing source references. We also detail the system design and fine-tuning methodology, demonstrating that grounding answers in retrieved evidence reduces unsupported content by approximately 60%. These results highlight the potential of RAG-augmented open-source LLMs for reliable biomedical QA, pointing toward practical clinical informatics applications.

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。