# Rethinking the Role of Token Retrieval in Multi-Vector Retrieval

arXiv: https://arxiv.org/abs/2304.01982 · HTML: https://mlsanity.com/paper/2304.01982/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 50 references that are in the map.
- First posted on arXiv 4 Apr 2023.

## Builds on (most cited first, 30 of 44)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)
- [Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring](https://mlsanity.com/paper/1905.01969/) (2019)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [Condenser: a Pre-training Architecture for Dense Retrieval](https://mlsanity.com/paper/2104.08253/) (2021)
- [Pre-training Tasks for Embedding-based Large-scale Retrieval](https://mlsanity.com/paper/2002.03932/) (2020)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval](https://mlsanity.com/paper/2109.10086/) (2021)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List](https://mlsanity.com/paper/2104.07186/) (2021)
- [Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)](https://mlsanity.com/paper/1405.5869/) (2014)
- [PLAID: An Efficient Engine for Late Interaction Retrieval](https://mlsanity.com/paper/2205.09707/) (2022)

## Built on by (most cited first, 30 of 31)

- [ColPali: Efficient Document Retrieval with Vision Language Models](https://mlsanity.com/paper/2407.01449/) (2024)
- [MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction](https://mlsanity.com/paper/2509.18095/) (2025)
- [Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling](https://mlsanity.com/paper/2409.14683/) (2024)
- [DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning](https://mlsanity.com/paper/2509.23883/) (2025)
- [Efficient Constant-Space Multi-Vector Retrieval](https://mlsanity.com/paper/2504.01818/) (2025)
- [Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing](https://mlsanity.com/paper/2410.01727/) (2024)
- [Matchmaker: Self-Improving Large Language Model Programs for Schema Matching](https://mlsanity.com/paper/2410.24105/) (2024)
- [Generative Retrieval as Multi-Vector Dense Retrieval](https://mlsanity.com/paper/2404.00684/) (2024)
- [Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval](https://mlsanity.com/paper/2604.10167/) (2026)
- [ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval](https://mlsanity.com/paper/2402.15059/) (2024)
- [Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations](https://mlsanity.com/paper/2603.01666/) (2026)
- [Simple Projection Variants Improve ColBERT Performance](https://mlsanity.com/paper/2510.12327/) (2025)
- [MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework](https://mlsanity.com/paper/2606.07654/) (2026)
- [LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention](https://mlsanity.com/paper/2607.11976/) (2026)
- [Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense Encoders](https://mlsanity.com/paper/2311.09765/) (2023)
- [LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026](https://mlsanity.com/paper/2511.00444/) (2025)
- [LEMUR: Learned Multi-Vector Retrieval](https://mlsanity.com/paper/2601.21853/) (2026)
- [GEM: A Native Graph-based Index for Multi-Vector Retrieval](https://mlsanity.com/paper/2603.20336/) (2026)
- [LLM-Oriented Information Retrieval: A Denoising-First Perspective](https://mlsanity.com/paper/2605.00505/) (2026)
- [No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval](https://mlsanity.com/paper/2605.30120/) (2026)
- [TileMaxSim: IO-Aware GPU MaxSim Scoring with Dimension Tiling and Fused Product Quantization](https://mlsanity.com/paper/2606.26439/) (2026)
- [EigenLI: Spectral Approximations to Late Interaction](https://mlsanity.com/paper/2609.07561/) (2026)
- [PROTOCOL: Late Interaction Retrieval for Protein Homolog Search](https://mlsanity.com/paper/2605.29158/) (2026)
- [ColBERTSaR: Sparsified ColBERT Index via Product Quantization](https://mlsanity.com/paper/2606.05568/) (2026)
- [PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID](https://mlsanity.com/paper/2607.18626/) (2026)
- [MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkish](https://mlsanity.com/paper/2608.26344/) (2026)
- [Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval](https://mlsanity.com/paper/2608.29951/) (2026)
- [Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval](https://mlsanity.com/paper/2609.07262/) (2026)
- [BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval](https://mlsanity.com/paper/2609.25859/) (2026)
- [Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence](https://mlsanity.com/paper/2610.13277/) (2026)

## Abstract (arXiv)

Multi-vector retrieval models such as ColBERT [Khattab and Zaharia, 2020] allow token-level interactions between queries and documents, and hence achieve state of the art on many information retrieval benchmarks. However, their non-linear scoring function cannot be scaled to millions of documents, necessitating a three-stage process for inference: retrieving initial candidates via token retrieval, accessing all token vectors, and scoring the initial candidate documents. The non-linear scoring function is applied over all token vectors of each candidate document, making the inference process complicated and slow. In this paper, we aim to simplify the multi-vector retrieval by rethinking the role of token retrieval. We present XTR, ConteXtualized Token Retriever, which introduces a simple, yet novel, objective function that encourages the model to retrieve the most important document tokens first. The improvement to token retrieval allows XTR to rank candidates only using the retrieved tokens rather than all tokens in the document, and enables a newly designed scoring stage that is two-to-three orders of magnitude cheaper than that of ColBERT. On the popular BEIR benchmark, XTR advances the state-of-the-art by 2.8 nDCG@10 without any distillation. Detailed analysis confirms our decision to revisit the token retrieval stage, as XTR demonstrates much better recall of the token retrieval stage compared to ColBERT.