Colbertv2: Effective And Efficient Retrieval Via Lightweight Late Interaction

Abstract

Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-vector representations, late interaction models produce multi-vector representations at the granularity of each token and decompose relevance modeling into scalable token-level computations. This decomposition has been shown to make late interaction more effective, but it inflates the space footprint of these models by an order of magnitude. In this work, we introduce ColBERTv2, a retriever that couples an aggressive residual compression mechanism with a denoised supervision strategy to simultaneously improve the quality and space footprint of late interaction. We evaluate ColBERTv2 across a wide range of benchmarks, establishing state-of-the-art quality within and outside the training domain while reducing the space footprint of late interaction models by 6--10\(\times\).

Stats

• citations212
• S2 citations—
• github stars0
• HF likes0
• heat score17.46
• arxiv keysanthanam2021colbertv2

Related papers

• Colbert: Efficient And Effective Passage Search Via Contextualized Late Interaction Over BERT (2020)0.00
• Colbert-att: Late-interaction Meets Attention For Enhanced Retrieval (2026)0.00
• Introducing Neural Bag Of Whole-words With Colberter: Contextualized Late Interactions Using Enhanced Reduction (2022)0.00
• Pylate: Flexible Training And Retrieval For Late Interaction Models (2025)3.58
• Jina-colbert-v2: A General-purpose Multilingual Late Interaction Retriever (2024)5.24
• Diagnosable Colbert: Debugging Late-interaction Retrieval Models Using A Learned Latent Space As Reference (2026)0.00
• Turkcolbert: A Benchmark Of Dense And Late-interaction Models For Turkish Information Retrieval (2025)0.00
• Video-colbert: Contextualized Late Interaction For Text-to-video Retrieval (2025)5.24