Pith. sign in

REVIEW 19 cited by

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.12832 v2 pith:EUUBRITO submitted 2020-04-27 cs.IR cs.CL

Omar Khattab , Matei Zaharia This is my paper · ORCID
classification cs.IRcs.CL
keywords colbertinteractiondocumentmodelsbertdeepqueryranking
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking models based on these LMs increase computational cost by orders of magnitude over prior approaches, particularly as they must feed each query-document pair through a massive neural network to compute a single relevance score. To tackle this, we present ColBERT, a novel ranking model that adapts deep LMs (in particular, BERT) for efficient retrieval. ColBERT introduces a late interaction architecture that independently encodes the query and the document using BERT and then employs a cheap yet powerful interaction step that models their fine-grained similarity. By delaying and yet retaining this fine-granular interaction, ColBERT can leverage the expressiveness of deep LMs while simultaneously gaining the ability to pre-compute document representations offline, considerably speeding up query processing. Beyond reducing the cost of re-ranking the documents retrieved by a traditional model, ColBERT's pruning-friendly interaction mechanism enables leveraging vector-similarity indexes for end-to-end retrieval directly from a large document collection. We extensively evaluate ColBERT using two recent passage search datasets. Results show that ColBERT's effectiveness is competitive with existing BERT-based models (and outperforms every non-BERT baseline), while executing two orders-of-magnitude faster and requiring four orders-of-magnitude fewer FLOPs per query.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RAG-Stack: Co-Optimizing RAG Serving Performance and Quality

    cs.DB 2026-08 conditional novelty 7.0 of 10

    RAG-Stack jointly optimizes RAG algorithm choices and serving-system settings via sub-metric-aware multi-objective Bayesian optimization plus an analytical performance model, reporting Pareto frontiers covering 52.5% ...

  2. BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

    cs.CL 2026-07 conditional novelty 7.0 of 10

    On an enterprise corpus scaled from 1.7M to 601M tokens, BM25 beats raw-file agentic search, dense retrieval, and graph RAG at large sizes, crossing near 10M tokens.

  3. AutoIndex: Learning Representation Programs for Retrieval

    cs.IR 2026-07 conditional novelty 6.0 of 10

    AutoIndex's agentic search over document-preprocessing programs improves BM25 Recall@100 on all 8 CRUMB tasks by an average of +8.4% relative to full-document indexing.

  4. Semantic Homogenization in Italian Popular Music: A Diachronic Analysis

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Sanremo lyrics exhibit rising semantic homogeneity over decades, consistently recovered by full-text, portion, topic and word-level embedding analyses.

  5. NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks

    cs.CL 2025-08 conditional novelty 6.0 of 10

    NLKI combines fine-tuned dense retrieval, LLM-generated explanations, and noise-robust losses to improve small VLMs on commonsense VQA.

  6. Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A new 4,978-item medical QA benchmark shows modern LLMs handle true/false and multiple choice well but struggle with list questions and multi-hop reasoning.

  7. Build the web for agents, not agents for the web

    cs.LG 2025-06 conditional novelty 6.0 of 10

    The paper proposes a paradigm shift: design a standardized Agentic Web Interface for AI agents, rather than adapting agents to human-facing websites.

  8. Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings

    cs.IR 2025-05 conditional novelty 6.0 of 10

    A new benchmark (ConTEB) and training method (InSeNT) show that context-aware chunk embeddings greatly improve retrieval on context-dependent queries, with minimal computational overhead.

  9. Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

    cs.AI 2026-07 conditional novelty 5.0 of 10

    An MCP server with vector schema retrieval and Steiner-tree join planning lets LLMs query MathModDB in natural language while staying on curated ontology paths and linking out to Dataverse.

  10. FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation

    cs.CL 2025-06 conditional novelty 5.0 of 10

    FlexRAG is a modular, open-source RAG framework with text, multimodal, and web retrieval, plus evaluation tools and efficient memory-mapped indexing.

  11. SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking

    cs.IR 2026-07 conditional novelty 4.0 of 10

    A zero-shot Qwen2.5-14B reranker on top of BM25+E5 hybrid retrieval reaches 64.39 MRR@5 on CLEF-2026 CheckThat! Task 1 English scientific source retrieval, with the LLM contributing most of the gain.

  12. JobMatchAI-An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI

    cs.AI 2026-03 conditional novelty 4.0 of 10

    On the new JobSearch-XS benchmark, the hybrid JobMatchAI pipeline reaches NDCG@10 of 0.81 (about 7% over BM25) with a white-box, factor-level reranker and LLM explanations.

  13. Vector embedding of multi-modal texts: a tool for discovery?

    cs.IR 2025-09 conditional novelty 4.0 of 10

    Using ColPali embeddings of 3,600 textbook page images, cosine similarity beats dot product, Euclidean, and Manhattan distances on top-5 retrieval, but only reaches 0.51 precision@5 without a text-only baseline.

  14. RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring

    cs.CY 2025-08 reject novelty 4.0 of 10

    A RAG-based adaptive tutoring framework for cybersecurity training is presented and evaluated on a small synthetic QA dataset, reporting high faithfulness and relevancy for GPT-4, but with inconsistent metrics and no ...

  15. Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data

    cs.CL 2025-07 reject novelty 4.0 of 10

    An enterprise RAG framework combining hybrid retrieval, cross-encoder reranking, and structure-aware table indexing claims relative gains of 15% in Precision@5, 13% in Recall@5, and 16% in MRR over a dense-only baseline.

  16. Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker

    cs.IR 2025-07 conditional novelty 4.0 of 10

    A two-stage OpenSearch retriever plus ColPali late-interaction re-ranker matches full late-interaction recall@1 on ViDoRe while using 14 to 53 pages instead of hundreds to thousands per query.

  17. DoTA-RAG: Dynamic of Thought Aggregation RAG

    cs.CL 2025-06 conditional novelty 4.0 of 10

    DoTA-RAG combines query rewriting, namespace routing, dense retrieval, BM25 pruning, and reranking to answer questions over a 15M-document corpus, with reported correctness gains but fragile faithfulness under output caps.

  18. Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models

    cs.IR 2025-05 reject novelty 4.0 of 10

    In tri-modal hybrid retrieval with GPT-4o reranking, MiniLM-v6 matches or beats BGE-Large on SciFact, FIQA, and NFCorpus despite being far smaller.

  19. The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

    cs.AI 2026-06 unverdicted novelty 2.0 of 10

    A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.

Pith tools