mlsanityData to 7 Oct 2026

PLAID: An Efficient Engine for Late Interaction Retrieval

arXiv 2205.09707 ↗First posted 19 May 2022cs.IR cs.CLcited by 95

Not on the map. Why?

Abstract (arXiv)

Pre-trained language models are increasingly important components across multiple information retrieval (IR) paradigms. Late interaction, introduced with the ColBERT model and recently refined in ColBERTv2, is a popular paradigm that holds state-of-the-art status across many benchmarks. To dramatically speed up the search latency of late interaction, we introduce the Performance-optimized Late Interaction Driver (PLAID). Without impacting quality, PLAID swiftly eliminates low-scoring passages using a novel centroid interaction mechanism that treats every passage as a lightweight bag of centroids. PLAID uses centroid interaction as well as centroid pruning, a mechanism for sparsifying the bag of centroids, within a highly-optimized engine to reduce late interaction search latency by up to 7× on a GPU and 45× on a CPU against vanilla ColBERTv2, while continuing to deliver state-of-the-art retrieval quality. This allows the PLAID engine with ColBERTv2 to achieve latency of tens of milliseconds on a GPU and tens or just few hundreds of milliseconds on a CPU at large scale, even at the largest scales we evaluate with 140M passages.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 19 May 2022.

Builds on

34 of 56 references.

References · 34

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  2. 2017Billion-scale similarity search with GPUscited by 2,477
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  4. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  5. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  6. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  7. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  8. 2019Passage Re-ranking with BERTcited by 629
  9. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  10. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  11. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 283
  12. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
22 more
  1. 2019Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoringcited by 164
  2. 2020Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillationcited by 143
  3. 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 126
  4. 2021COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted Listcited by 113
  5. 2019CEDR: Contextualized Embeddings for Document Rankingcited by 77
  6. 2020Relevance-guided Supervision for OpenQA with ColBERTcited by 71
  7. 2021Learning Passage Impacts for Inverted Indexescited by 68
  8. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  9. 2021Hindsight: Posterior-guided training of retrievers for improved open-ended generationcited by 38
  10. 2022Curriculum Learning for Dense Retrieval Distillationcited by 38
  11. 2021Pseudo-Relevance Feedback for Multiple Representation Dense Retrievalcited by 31
  12. 2021A Proposed Conceptual Framework for a Representational Approach to Information Retrievalcited by 24
  13. 2022Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reductioncited by 21
  14. 2022RELIC: Retrieving Evidence for Literary Claimscited by 18
  15. 2021Learning Cross-Lingual IR from an English Retrievercited by 16
  16. 2021Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluationcited by 15
  17. 2020Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficientlycited by 10
  18. 2022Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrievalcited by 9
  19. 2022Zero-shot Query Contextualization for Conversational Searchcited by 9
  20. 2021On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrievalcited by 7
  21. 2021Query Embedding Pruning for Dense Retrievalcited by 5
  22. 2021On Single and Multiple Representations in Dense Passage Retrievalcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 9; 2024: 18; 2025: 23; 2026: 39.

95 papers.

Sort:

By area:

  1. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  2. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 190
  3. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 116
  4. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  5. 2023Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answeringcited by 51
  6. 2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
  7. 2024PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrieverscited by 42
  8. 2023UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankerscited by 37
  9. 2025MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interactioncited by 36
  10. 2023Rethinking the Role of Token Retrieval in Multi-Vector Retrievalcited by 28
  11. 2023NevIR: Negation in Neural Information Retrievalcited by 28
  12. 2022An Efficiency Study for SPLADE Modelscited by 26
38 more
  1. 2024KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checkingcited by 26
  2. 2024Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Poolingcited by 23
  3. 2024Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillationcited by 22
  4. 2022CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrievalcited by 19
  5. 2025DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruningcited by 19
  6. 2022Neural Approaches to Multilingual Information Retrievalcited by 18
  7. 2025PyLate: Flexible Training and Retrieval for Late Interaction Modelscited by 17
  8. 2024JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resourcescited by 15
  9. 2025Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrievalcited by 13
  10. 2025Efficient Constant-Space Multi-Vector Retrievalcited by 10
  11. 2025Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimizationcited by 10
  12. 2024A Reproducibility Study of PLAIDcited by 8
  13. 2026Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Frameworkcited by 8
  14. 2026Multi-Vector Index Compression in Any Modalitycited by 8
  15. 2023ESPN: Memory-Efficient Multi-Vector Information Retrievalcited by 7
  16. 2025VIBE: Vector Index Benchmark for Embeddingscited by 6
  17. 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalcited by 5
  18. 2026OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queriescited by 5
  19. 2022Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarkingcited by 4
  20. 2023PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Developmentcited by 4
  21. 2023Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrievalcited by 4
  22. 2025Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Searchcited by 4
  23. 2025Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracycited by 4
  24. 2026Taxonomy of the Retrieval System Framework: Pitfalls and Paradigmscited by 4
  25. 2024PLAID SHIRTTT for Large-Scale Streaming Dense Retrievalcited by 3
  26. 2024PairDistill: Pairwise Relevance Distillation for Dense Retrievalcited by 3
  27. 2024MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrievalcited by 3
  28. 2024AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Datasetcited by 2
  29. 2025Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answeringcited by 2
  30. 2025Towards Lossless Token Pruning in Late-Interaction Retrieval Modelscited by 2
  31. 2025CLIRudit: Cross-Lingual Information Retrieval of Scientific Documentscited by 2
  32. 2025Simple Projection Variants Improve ColBERT Performancecited by 2
  33. 2025Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answeringcited by 2
  34. 2026IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answeringcited by 2
  35. 2026GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexingcited by 2
  36. 2026MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Frameworkcited by 2
  37. 2026Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrievalcited by 2
  38. 2024HLTCOE at TREC 2023 NeuCLIR Trackcited by 1

50 most cited of 95 All 95 (JSON)