用大模型自动生成假文档，让医学检索无需标注数据也能精准找知识。
AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels
- 用大模型生成带医学上下文的假文档，引导检索器找真答案。
- 在中文医疗检索基准上，效果远超传统方法，且适配多种模型配置。
- 适合没有标注数据却需高精度检索的医疗AI研发人员。
医学信息检索（MIR）对于从电子病历、科学文献和医学数据库中获取相关知识至关重要。然而，由于缺乏相关性标注数据，实现有效的零样本密集检索仍面临巨大挑战。本文提出一种新方法——自学习假文档嵌入（SL-HyDE），利用大语言模型（LLMs）作为生成器，基于查询生成假设性文档，这些文档包含关键医学上下文，引导密集检索器识别最相关文档。该自学习框架通过无标注医学语料逐步优化伪文档生成与检索能力，完全不依赖相关性标注数据。此外，我们构建了中文医学信息检索基准（CMIRB），涵盖五个任务和十个数据集，基于真实医疗场景进行评估。在十种模型上基准测试表明，SL-HyDE显著优于HyDE，在多种大模型与检索器配置下均展现出强大泛化性与可扩展性。代码与数据已公开于：https://github.com/ll0ruc/AutoMIR
原文摘要 · Abstract (English)
Medical information retrieval (MIR) is essential for retrieving relevant medical knowledge from diverse sources, including electronic health records, scientific literature, and medical databases. However, achieving effective zero-shot dense retrieval in the medical domain poses substantial challenges due to the lack of relevance-labeled data. In this paper, we introduce a novel approach called \textbf{S}elf-\textbf{L}earning \textbf{Hy}pothetical \textbf{D}ocument \textbf{E}mbeddings (\textbf{SL-HyDE}) to tackle this issue. SL-HyDE leverages large language models (LLMs) as generators to generate hypothetical documents based on a given query. These generated documents encapsulate key medical context, guiding a dense retriever in identifying the most relevant documents. The self-learning framework progressively refines both pseudo-document generation and retrieval, utilizing unlabeled medical corpora without requiring any relevance-labeled data. Additionally, we present the Chinese Medical Information Retrieval Benchmark (CMIRB), a comprehensive evaluation framework grounded in real-world medical scenarios, encompassing five tasks and ten datasets. By benchmarking ten models on CMIRB, we establish a rigorous standard for evaluating medical information retrieval systems. Experimental results demonstrate that SL-HyDE significantly surpasses HyDE in retrieval accuracy while showcasing strong generalization and scalability across various LLM and retriever configurations. Our code and data are publicly available at: https://github.com/ll0ruc/AutoMIR
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。