Pith. sign in

REVIEW 12 cited by

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

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 2112.01488 v3 pith:KBNTB5YJ submitted 2021-12-02 cs.IR cs.CL

Keshav Santhanam , Omar Khattab , Jon Saad-Falcon , Christopher Potts , Matei Zaharia This is my paper
classification cs.IRcs.CL
keywords interactionlatecolbertv2footprintmodelsspaceeffectiveneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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$\times$.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

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

  1. 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.

  2. OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning

    cs.CL 2025-10 reject novelty 6.0 of 10

    A tool-augmented reward model trained with GRPO on 27K synthetic pairs beats existing reward models on long-form QA judgment and improves downstream alignment.

  3. Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    ZEST shows that a small synthetic corpus generated by GPT-4o from five examples can stand in for the real target corpus in a frozen context-aware embedding model, losing under 0.5% retrieval accuracy on MTEB.

  4. Identifying Origins of Place Names via Retrieval Augmented Generation

    cs.IR 2025-08 conditional novelty 5.0 of 10

    A RAG pipeline using ColBERTv2 and Llama2 retrieves Melbourne street-name origins from DBpedia, but language models under-use spatial context, limiting top-1 accuracy.

  5. 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.

  6. ASARL: Autonomous Social-Aware Relevance Learning for QQ Search

    cs.IR 2026-07 conditional novelty 4.0 of 10

    An agent-loop data-curation pipeline with social-aware chain-of-thought, preference, and distillation training improves QQ group/channel search relevance in offline and online evaluation.

  7. 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.

  8. HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data

    cs.IR 2025-08 conditional novelty 4.0 of 10

    A hybrid retrieval system that combines LLM-generated attribute filters with embedding search outperforms several baselines on a small, curated semi-structured product benchmark.

  9. Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

    cs.CL 2025-07 conditional novelty 4.0 of 10

    An Arabic dense retriever using a trainable attentive scoring module instead of dot-product similarity reports improved top-k passage retrieval on ArabicaQA.

  10. GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval

    cs.IR 2025-06 conditional novelty 4.0 of 10

    GOLFer filters hallucinated sentences from small-LM-generated hypothetical documents and reweights the rest into the query, improving retrieval at lower cost than large LLM expansion.

  11. Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization

    cs.CL 2025-05 conditional novelty 4.0 of 10

    XSum, a question-generation plus editor RAG pipeline, produces survey-style summaries from multiple scientific papers and reports improved scores on the SurveySum benchmark.

  12. Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation

    cs.IR 2025-07 reject novelty 3.0 of 10

    A query-level score combining quantization stability and neighborhood density predicts retrieval performance and is claimed to improve Recall@10 by only 2 to 3 percent per dataset.

Pith tools