Metraipolis › archive › dc_8cf94223dc3e
Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning — arXiv:2609.36359
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36359
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:22:31.632Z
- SHA-256 of the archived text
18b8fa6d2d7cedae4102f31084afd2be2d12166dc0869d84e7b36cb496549fe8- Stable URL of this page
https://metraipolis.com/documento/dc_8cf94223dc3e
How to cite
Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning — arXiv:2609.36359 — arXiv (en), https://arxiv.org/abs/2609.36359 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8cf94223dc3e (Metraipolis archive dc_8cf94223dc3e, sha256 18b8fa6d2d7cedae4102f31084afd2be2d12166dc0869d84e7b36cb496549fe8)
BibTeX
@misc{dc8cf94223dc3e,
title = {Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning — arXiv:2609.36359},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36359},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8cf94223dc3e; sha256 18b8fa6d2d7cedae4102f31084afd2be2d12166dc0869d84e7b36cb496549fe8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36359. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.36359 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.491Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).