SLIM: Sparsified Late Interaction For Multi-vector Retrieval With Inverted Indexes

Abstract

This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on various retrieval datasets, and among them, ColBERT is the most established method based on the late interaction of contextualized token embeddings of pre-trained language models. However, efficient ColBERT implementations require complex engineering and cannot take advantage of off-the-shelf search libraries, impeding their practical use. To address this issue, SLIM first maps each contextualized token vector to a sparse, high-dimensional lexical space before performing late interaction between these sparse token embeddings. We then introduce an efficient two-stage retrieval architecture that includes inverted index retrieval followed by a score refinement module to approximate the sparsified late interaction, which is fully compatible with off-the-shelf lexical search libraries such as Lucene. SLIM achieves

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keyli2023slim

Related papers

• Pylate: Flexible Training And Retrieval For Late Interaction Models (2025)3.58
• Colbertv2: Effective And Efficient Retrieval Via Lightweight Late Interaction (2021)17.46
• Efficient Inverted Indexes For Approximate Retrieval Over Learned Sparse Representations (2024)11.67
• Col-bandit: Zero-shot Query-time Pruning For Late-interaction Retrieval (2026)0.00
• Hybrid Inverted Index Is A Robust Accelerator For Dense Retrieval (2022)7.07
• CITADEL: Conditional Token Interaction Via Dynamic Lexical Routing For Efficient And Effective Multi-vector Retrieval (2022)13.05
• Jina-colbert-v2: A General-purpose Multilingual Late Interaction Retriever (2024)5.24
• Reducing The Footprint Of Multi-vector Retrieval With Minimal Performance Impact Via Token Pooling (2024)0.00