发表机构
University of Wisconsin–Madison; MIT（威斯康星大学麦迪逊分校; 麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图索引构建与语义评估不匹配问题，提出LLM引导的图剪枝（LGP）框架，通过替换低价值邻居改进ANN图索引，在DiskANN和HNSW上提升端到端检索性能。
AI 中文摘要
基于图的近似最近邻搜索（ANNS）被广泛用于大规模语义搜索。其索引主要基于输入数据集（如文档或图像）中嵌入之间的几何关系构建，而非显式优化语义相关性。然而，当使用这些索引进行下游查询检索时，性能是基于检索结果与查询的语义相关性来评估的。这造成了索引构建方式与检索结果评估方式之间的根本性“几何-语义”不匹配。虽然现有的基于LLM的重排序方法可以在查询时部分缓解这种不匹配，但它们未能解决图中潜在的结构性问题。因此，我们提出了LLM引导的图剪枝（LGP），这是一个通用框架，通过利用LLM推理直接改进现有ANN图索引来解决这种不匹配。LGP识别出节点中结构上“低价值”的邻居，并用LLM选择的替代邻居替换它们，这些替代邻居提供有用的语义信息，同时保留原始图所需的几何结构，包括稀疏性和高效可导航性。在代表性语义检索基准上的实验表明，与普通的贪心图搜索和基于LLM的重排序相比，LGP在广泛使用的基于图的ANN索引（如DiskANN和HNSW）上持续提高了端到端检索性能。
英文摘要
Graph-based approximate nearest neighbor search (ANNS) is widely used for large-scale semantic search. Its indices are constructed primarily based on geometric relationships among embeddings of an input dataset (e.g., documents or images), rather than explicitly optimizing for semantic relevance. However, when using these indices for downstream query retrieval, performance is evaluated based on the semantic relevance of the retrieved results to the query. This creates a fundamental "geometry-semantic" mismatch between how the indices are constructed and how their retrieval results are evaluated. While existing LLM-based reranking methods can partially mitigate this mismatch at query time, they leave this underlying structural problem in the graph unresolved. We therefore propose LLM-Guided Graph Pruning (LGP), a general framework that addresses this mismatch directly by leveraging LLM reasoning to refine an existing ANN graph index itself. LGP identifies structurally "low-value" neighbors of nodes and replaces them with LLM-selected alternatives that provide useful semantic information while retaining desired geometric structures of the original graph, including sparsity and efficient navigability. Experiments on representative semantic retrieval benchmarks show that LGP consistently improves end-to-end retrieval performance over both vanilla greedy graph search and LLM-based reranking across widely used graph-based ANN indices such as DiskANN and HNSW.
Comments29 pages
