Pith. sign in

REVIEW 21 cited by

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

Not yet reviewed by Pith; the record is open.

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

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

classification cs.IR cs.CL
keywords interactionlatecolbertv2footprintmodelsspaceeffectiveneural
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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 with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

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

  1. Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings

    cs.DS 2026-06 unverdicted novelty 8.0

    Proves that for bounded n, there exist MV embeddings with m vectors each whose Chamfer matrix requires single-vector dimension D = (ε² m)^Ω(1/ε) to approximate within ε, separating MV from SV expressiveness.

  2. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

    cs.CL 2023-10 conditional novelty 8.0

    DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.

  3. HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions

    cs.IR 2026-06 unverdicted novelty 7.0

    HAKARI-Bench reconstructs 35 benchmarks into 551 tasks across 43 languages, reproducing full MTEB, MMTEB, and BEIR rankings with Spearman correlation above 0.97 while supporting efficiency variant comparisons.

  4. Spectral Retrieval: Multi-Scale Sinc Convolution over Token Embeddings for Localized Retrieval in LLM Multi-Agent Systems

    cs.IR 2026-05 unverdicted novelty 7.0

    Spectral Retrieval uses multi-scale sinc convolutions on token embeddings to interpolate between per-token MaxSim and mean-pooling, achieving large gains on synthetic and LIMIT-small benchmarks for localized retrieval.

  5. Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory

    cs.CL 2026-05 unverdicted novelty 7.0

    MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.

  6. Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization

    cs.CL 2025-10 unverdicted novelty 7.0

    GQR is a test-time optimization technique that refines primary retriever query embeddings using complementary retriever scores to achieve high performance with smaller representations in multimodal visual document retrieval.

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

    cs.CL 2026-07 conditional novelty 6.0

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

  8. ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation

    cs.IR 2026-04 unverdicted novelty 6.0

    ClusterRAG applies density-based clustering to user profiles for collaborative retrieval in personalized RAG and reports best performance on LaMP tasks by combining target and similar-user profiles.

  9. EmbeddingGemma: Powerful and Lightweight Text Representations

    cs.CL 2025-09 unverdicted novelty 6.0

    A 300M-parameter open embedding model sets new SOTA on MTEB for its size class and matches models twice as large while staying effective when compressed.

  10. LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations

    cs.IR 2025-09 conditional novelty 6.0

    LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.

  11. TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

    cs.LG 2025-04 unverdicted novelty 6.0

    TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a fac...

  12. RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

    cs.CL 2024-01 unverdicted novelty 6.0

    RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.

  13. Text and Code Embeddings by Contrastive Pre-Training

    cs.CL 2022-01 unverdicted novelty 6.0

    Contrastive pre-training on unsupervised data at scale creates text and code embeddings that set new state-of-the-art results on classification and semantic search benchmarks.

  14. CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval

    cs.IR 2026-06 unverdicted novelty 5.0

    CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced ev...

  15. Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering

    cs.IR 2026-05 unverdicted novelty 5.0

    Multi-task evaluation of 22 patent embedding models finds task-specific fine-tuning benefits and significant cross-landscape retrieval degradation that cannot be fixed by hybrid fusion.

  16. MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution

    cs.LG 2025-12 unverdicted novelty 5.0

    MaxShapley computes fair document attributions in generative QA by reducing Shapley value calculation to polynomial time via a max-sum utility, matching exact Shapley quality on HotPotQA, MuSiQUE, and MS MARCO while u...

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

    cs.IR 2026-07 conditional novelty 4.0

    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.

  18. Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking

    cs.CL 2026-05 unverdicted novelty 4.0

    InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-...

  19. Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation

    cs.CL 2026-03 unverdicted novelty 4.0

    A RAG framework integrates semantic search and LLMs to deliver time-annotated answers to natural-language questions on construction project meeting minutes, demonstrated on an industry dataset with public code and dat...

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

    cs.AI 2026-03 conditional novelty 4.0

    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.

  21. Negative Data Mining for Contrastive Learning in Dense Retrieval at IKEA.com

    cs.IR 2026-05 conditional novelty 3.0

    Structured negative mining with taxonomy and LLM judges improves offline category accuracy by 2.6% in IKEA search but yields no significant online engagement gains due to prevalent zero-click user behavior.