用检索增强生成解决医学长篇问答难题，提升临床决策支持能力
RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering
- 结合生物医学嵌入与FAISS索引实现精准文献检索
- 在PubMedQA上达0.29 ROUGE-1，微调后BERTScore提升81%
- 适合需要深度医学知识推理的研究者与临床辅助系统开发者
生物医学文献的快速增长给获取特定医疗信息带来挑战。现有生物医学问答系统多聚焦短答案，难以提供临床决策所需的完整解释。我们提出RAG-BioQA，一种用于长篇生物医学问答的检索增强生成框架。系统采用BioBERT嵌入与FAISS索引进行检索，并使用LoRA微调的FLAN-T5模型生成答案。训练数据来自PubMedQA、MedDialog和MedQuAD共18.1万组问答对，在预留的PubMedQA测试集上评估。对比四种检索策略：密集检索（FAISS）、BM25、ColBERT和MonoT5。结果表明，领域适配的密集检索优于零样本神经重排序器，最佳配置达0.24 BLEU-1和0.29 ROUGE-1。微调使BERTScore相比基线提升81%。我们已开源该框架，以支持可复现的生物医学问答研究。
原文摘要 · Abstract (English)
The rapidly growth of biomedical literature creates challenges acquiring specific medical information. Current biomedical question-answering systems primarily focus on short-form answers, failing to provide comprehensive explanations necessary for clinical decision-making. We present RAG-BioQA, a retrieval-augmented generation framework for long-form biomedical question answering. Our system integrates BioBERT embeddings with FAISS indexing for retrieval and a LoRA fine-tuned FLAN-T5 model for answer generation. We train on 181k QA pairs from PubMedQA, MedDialog, and MedQuAD, and evaluate on a held-out PubMedQA test set. We compare four retrieval strategies: dense retrieval (FAISS), BM25, ColBERT, and MonoT5. Our results show that domain-adapted dense retrieval outperforms zero-shot neural re-rankers, with the best configuration achieving 0.24 BLEU-1 and 0.29 ROUGE-1. Fine-tuning improves BERTScore by 81\% over the base model. We release our framework to support reproducible biomedical QA research.
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。