将语义扩展与向量几何分离，实现大规模生物医学文献精确检索
Separating Semantic Expansion from Linear Geometry for PubMed-Scale Vector Search
- 用大模型扩展查询为生物医学短语，检索在固定向量空间进行
- 256维int8向量下，对4000万条MEDLINE数据做精确余弦搜索
- 无需训练参数，适合追求高效精准的生物医学信息检索场景
我们提出一个PubMed规模的检索框架，将语义解释与度量几何分离。大语言模型将自然语言查询扩展为简洁的生物医学短语；检索在固定、均值为零、近似各向同性的嵌入空间中进行。文档和查询向量均作为词元嵌入的加权均值，投影到噪声轴的正交补空间，并通过Johnson-Lindenstrauss变换压缩。系统不需训练参数。在约4000万条MEDLINE记录的全集上，使用256维int8向量进行精确余弦搜索，可检索出连贯的生物医学聚类。评估仅基于几何特性：头余弦、紧凑性、中心闭合性与各向同性，与随机向量基线对比。由于语言模型扩展已定义有效目标集合，因此不定义召回率。
原文摘要 · Abstract (English)
We describe a PubMed scale retrieval framework that separates semantic interpretation from metric geometry. A large language model expands a natural language query into concise biomedical phrases; retrieval then operates in a fixed, mean free, approximately isotropic embedding space. Each document and query vector is formed as a weighted mean of token embeddings, projected onto the complement of nuisance axes and compressed by a Johnson Lindenstrauss transform. No parameters are trained. The system retrieves coherent biomedical clusters across the full MEDLINE corpus (about 40 million records) using exact cosine search on 256 dimensional int8 vectors. Evaluation is purely geometric: head cosine, compactness, centroid closure, and isotropy are compared with random vector baselines. Recall is not defined, since the language-model expansion specifies the effective target set.
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。