实证分析医学检索管道的性能与效率权衡，给出可落地的设计建议。
A Systematic Study of Biomedical Retrieval Pipeline Trade-offs in Performance and Efficiency
- 系统测试不同数据集、分块粒度和索引配置对检索效果的影响。
- 发现聚合语料库在绝对精度上最优，MedRAG/pubmed在图索引下表现最佳。
- 适合医学NLP研究者构建高效检索系统时参考决策路径。
检索系统在生物医学与临床自然语言处理中日益重要，但实际构建指南有限。本文通过大规模实证研究，分析检索管道设计选择对性能与效率的影响。我们基于多个公开生物医学文本数据集，采用多种查询类型（包括考试题、对话式医疗问题、社区提问及非疑问句）测试了不同语料库选择、分块粒度和向量索引配置下的检索效果。使用大模型作为裁判的鲁棒胜率对比评估方法，并结合人工验证确保结果可靠性。实验表明，语料库聚合能显著提升绝对检索质量；在基于图的（HNSW）索引下，MedRAG/pubmed为单一语料库中的帕累托最优选择；合适的分块策略与FAISS索引组合可在速度与效率间实现最佳平衡。
原文摘要 · Abstract (English)
Retrieval systems are increasingly used in biomedical and clinical natural language processing applications, yet practical guidance for researchers building such systems is limited. In this work, we provide such guidance through an empirical study of how retrieval pipeline design choices affect performance and efficiency at scale. In particular, we examine retrieval over a variety of existing, public biomedical text datasets, leveraging a variety of disparate types of queries, including exam-style questions, conversational medical queries, community-asked questions, and non-question formulations across various retrieval pipeline settings spanning corpus selection, chunk granularity, and vector index configuration. Retrieval results are judged using a robust, win-rate comparison assessment via an LLM-as-a-judge setting with human validation. Across these experiments, we identify several points of concrete guidance for reviewers, including the superiority of corpus aggregation for absolute retrieval quality, and the emergence of MedRAG/pubmed as the Pareto-optimal singleton corpus under graph-based (HNSW) indexing, appropriate chunking strategies, and FAISS indexing choices that offer the best trade-offs in speed and efficiency.
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。