用检索增强生成提升生物医学问答效率与可复现性
Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented Generation
- 采用混合检索策略，先用BM25粗筛再用MedCPT精排
- 50篇文档检索时准确率与召回率均达90%，响应时间1.91秒
- 系统开源可复现，适合科研与临床辅助问答场景
生物医学问答系统需兼顾准确性、效率与可扩展性。本研究系统评估了用于生物医学QA的检索增强生成（RAG）系统，考察不同检索策略与响应时间的权衡。在约10%的PubMed数据集（240万篇文献）上测试了BM25、BioBERT、MedCPT及混合方法，以及Elasticsearch、MongoDB和FAISS等数据存储方式，评估索引效率、检索延迟与端到端性能。基于此结果，在完整2400万篇PubMed语料库上部署最终系统，对比不同检索器的影响。结果显示，先用BM25检索50篇文档，再用MedCPT重排序，在准确率（0.90）、召回率（0.90）与响应时间（1.91秒）间达到最优平衡。BM25检索耗时稳定在82毫秒，而MedCPT承担主要计算开销。这些发现揭示了生物医学QA中检索深度、效率与可扩展性的关键权衡。系统代码开源，具备完全可复现性与可扩展性。
原文摘要 · Abstract (English)
Biomedical question-answering (QA) systems require effective retrieval and generation components to ensure accuracy, efficiency, and scalability. This study systematically examines a Retrieval-Augmented Generation (RAG) system for biomedical QA, evaluating retrieval strategies and response time trade-offs. We first assess state-of-the-art retrieval methods, including BM25, BioBERT, MedCPT, and a hybrid approach, alongside common data stores such as Elasticsearch, MongoDB, and FAISS, on a ~10% subset of PubMed (2.4M documents) to measure indexing efficiency, retrieval latency, and retriever performance in the end-to-end RAG system. Based on these insights, we deploy the final RAG system on the full 24M PubMed corpus, comparing different retrievers' impact on overall performance. Evaluations of the retrieval depth show that retrieving 50 documents with BM25 before reranking with MedCPT optimally balances accuracy (0.90), recall (0.90), and response time (1.91s). BM25 retrieval time remains stable (82ms), while MedCPT incurs the main computational cost. These results highlight previously not well-known trade-offs in retrieval depth, efficiency, and scalability for biomedical QA. With open-source code, the system is fully reproducible and extensible.
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。