Metraipolis › archive › dc_2caf9dfcadee
MV-IVF: Multi-Vector Retrieval via Multi-Vector Clustering — arXiv:2611.09040
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09040
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:44:55.568Z
- SHA-256 of the archived text
bb73bfef9efbc0dd40167195f6aedb833b302affa4cee2da446ee5f0e7d3238e- Stable URL of this page
https://metraipolis.com/documento/dc_2caf9dfcadee
How to cite
MV-IVF: Multi-Vector Retrieval via Multi-Vector Clustering — arXiv:2611.09040 — arXiv (en), https://arxiv.org/abs/2611.09040 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2caf9dfcadee (Metraipolis archive dc_2caf9dfcadee, sha256 bb73bfef9efbc0dd40167195f6aedb833b302affa4cee2da446ee5f0e7d3238e)
BibTeX
@misc{dc2caf9dfcadee,
title = {MV-IVF: Multi-Vector Retrieval via Multi-Vector Clustering — arXiv:2611.09040},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09040},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2caf9dfcadee; sha256 bb73bfef9efbc0dd40167195f6aedb833b302affa4cee2da446ee5f0e7d3238e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09040. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-vector retrieval represents each query and document as a set of embeddings and scores relevance via fine-grained set-to-set interactions such as MaxSim (Chamfer similarity). This expressiveness improves retrieval quality over single-vector representations, but makes search substantially more expensive. Existing systems address this challenge primarily through proxy representations or filter-and-rerank pipelines that reduce candidate generation to single-vector search. We study the complementary direction of building a native IVF-style index directly over multi-vector data. We introduce MV-IVF, an inverted-file index for multi-vector retrieval built on MV-Lloyd, a new Lloyd-style algorithm for clustering point clouds under a Chamfer objective. Our key observation is that once point clouds are assigned to clusters, the center-update step reduces to standard single-vector clustering over the flattened embeddings in each cluster. This enables efficient construction of a hierarchical IVF tree with center point clouds at internal nodes. At query time, MV-IVF performs best-first beam search over the tree to identify promising leaf clusters, then scores the documents in those leaves. We further accelerate search using low-bit quantization, query compression, and cache-efficient batched search. We implement MV-IVF in MVSIC, an optimized C++ library and unified evaluation framework for multi-vector retrieval that includes several major approaches. Across BEIR and LoTTE text retrieval benchmarks, MV-IVF achieves strong latency--recall tradeoffs, the best batched throughput frontiers, and favorable build-time and index-size profiles. At $90\%$ Recall-$10$@$10$, MV-IVF achieves up to $8.03\times$ lower single-query latency and up to $173.5\times$ higher QPS than the baselines, demonstrating that native IVF-style indexing is practical and effective for scalable multi-vector retrieval. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Databases (cs.DB). Pagina del lavoro: https://arxiv.org/abs/2611.09040 — 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 2026-11-09T22:37:32.240Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).