检索需要多向量：单向量与多向量嵌入的指数级分离

AI 摘要

该研究首次证明了在检索排序任务中，单向量嵌入与多向量嵌入之间存在指数级表达能力差距。作者构造了显式的查询-文档相关性矩阵族，其中多向量嵌入只需多项式大小即可正确排序，而单向量嵌入需要指数大小。基于理论构造，他们提出了ANDOR基准，实验显示单向量模型在零样本和微调后均表现不佳，而多向量模型持续领先，验证了理论预测。

正文节选

Retrieval Needs Multivectors: An Exponential Separation Abstract Recent works have highlighted the expressive limitations of embedding based retrieval models through both theoretical analyses and challenging benchmarks such as LIMIT. While multi-vector embeddings consistently outperform single-vector embeddings, the precise representational gap between them remains poorly understood. In this work, following Jayaram’s work, we provide the first explicit family of query and document sets, together

发布时间：2026-08-25 12:00

抓取时间：2026-08-25 12:50

来源机构：arXiv