LEMUR: Learned Multi-Vector Retrieval

• URL: http://arxiv.org/abs/2601.21853v1
• Date: Thu, 29 Jan 2026 15:26:32 GMT
• Title: LEMUR: Learned Multi-Vector Retrieval
• Authors: Elias Jääsaari, Ville Hyvönen, Teemu Roos,
• Abstract summary: We introduce LEMUR, a framework for multi-vector similarity search.<n>LEMUR consists of two consecutive problem reductions.<n>LEMUR is an order of magnitude faster than earlier multi-vector similarity search methods.
• Score: 9.22384870426709
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both queries and documents are encoded using one embedding for each token, and similarity between queries and documents is measured by the MaxSim similarity measure. However, the improved recall of multi-vector retrieval comes at the expense of significantly increased latency. This necessitates designing efficient approximate nearest neighbor search (ANNS) algorithms for multi-vector search. In this work, we introduce LEMUR, a simple-yet-efficient framework for multi-vector similarity search. LEMUR consists of two consecutive problem reductions: We first formulate multi-vector similarity search as a supervised learning problem that can be solved using a one-hidden-layer neural network. Second, we reduce inference under this model to single-vector similarity search in its latent space, which enables the use of existing single-vector ANNS methods for speeding up retrieval. In addition to performance evaluation on ColBERTv2 embeddings, we evaluate LEMUR on embeddings generated by modern multi-vector text models and multi-vector visual document retrieval models. LEMUR is an order of magnitude faster than earlier multi-vector similarity search methods.

Related papers

• Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy [36.03315207229038]
  HEAVEN is a two-stage hybrid-vector framework for visually rich document retrieval.<n>It efficiently retrieves candidate pages using a single-vector method over Visually-Summarized Pages.<n>It reranks candidates with a multi-vector method while filtering query tokens by linguistic importance to reduce redundant computations.
  arXiv  Detail & Related papers  (2025-10-25T08:27:37Z)
• Investigating Multi-layer Representations for Dense Passage Retrieval [46.25475369974163]
  We denote Multi-layer Representations (MLR) to make up the representation of a document.<n>We first investigate how representations in different layers affect MLR's performance under the multi-vector retrieval setting.<n>We propose to leverage pooling strategies to reduce multi-vector models to single-vector ones to improve retrieval efficiency.
  arXiv  Detail & Related papers  (2025-09-28T13:00:53Z)
• MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings [15.275864151890511]
  We introduce MUVERA (MUlti-VEctor Retrieval Algorithm), a retrieval mechanism which reduces multi-vector search to single-vector similarity search. MUVERA achieves consistently good end-to-end recall and latency across a diverse set of the BEIR retrieval datasets.
  arXiv  Detail & Related papers  (2024-05-29T20:40:20Z)
• Generative Retrieval as Multi-Vector Dense Retrieval [71.75503049199897]
  Generative retrieval generates identifiers of relevant documents in an end-to-end manner. Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval. We show that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document.
  arXiv  Detail & Related papers  (2024-03-31T13:29:43Z)
• Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control [66.78146440275093]
  Learned retrieval (LSR) is a family of neural methods that encode queries and documents into sparse lexical vectors. We explore the application of LSR to the multi-modal domain, with a focus on text-image retrieval. Current approaches like LexLIP and STAIR require complex multi-step training on massive datasets. Our proposed approach efficiently transforms dense vectors from a frozen dense model into sparse lexical vectors.
  arXiv  Detail & Related papers  (2024-02-27T14:21:56Z)
• LeanVec: Searching vectors faster by making them fit [1.0863382547662974]
  We present LeanVec, a framework that combines linear dimensionality reduction with vector quantization to accelerate similarity search on high-dimensional vectors. We show that LeanVec produces state-of-the-art results, with up to 3.7x improvement in search throughput and up to 4.9x faster index build time.
  arXiv  Detail & Related papers  (2023-12-26T21:14:59Z)
• An Efficient Algorithm for Clustered Multi-Task Compressive Sensing [60.70532293880842]
  Clustered multi-task compressive sensing is a hierarchical model that solves multiple compressive sensing tasks. The existing inference algorithm for this model is computationally expensive and does not scale well in high dimensions. We propose a new algorithm that substantially accelerates model inference by avoiding the need to explicitly compute these covariance matrices.
  arXiv  Detail & Related papers  (2023-09-30T15:57:14Z)
• CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval [72.90850213615427]
  Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers. These methods are orders of magnitude slower and need much more space to store their indices compared to their single-vector counterparts. We propose conditional token interaction via dynamic lexical routing, namely CITADEL, for efficient and effective multi-vector retrieval.
  arXiv  Detail & Related papers  (2022-11-18T18:27:35Z)
• Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization [60.91600465922932]
  We present an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoder. Our approach provides test-time recall-vs-computational cost trade-offs superior to the current widely-used methods.
  arXiv  Detail & Related papers  (2022-10-23T00:32:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.