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
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
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$\times$.
Forward citations
Cited by 21 Pith papers
-
Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings
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.
-
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
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.
-
HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
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.
-
Spectral Retrieval: Multi-Scale Sinc Convolution over Token Embeddings for Localized Retrieval in LLM Multi-Agent Systems
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.
-
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
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.
-
Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
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.
-
Semantic Homogenization in Italian Popular Music: A Diachronic Analysis
Sanremo lyrics exhibit rising semantic homogeneity over decades, consistently recovered by full-text, portion, topic and word-level embedding analyses.
-
ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
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.
-
EmbeddingGemma: Powerful and Lightweight Text Representations
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.
-
LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations
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.
-
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
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...
-
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
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.
-
Text and Code Embeddings by Contrastive Pre-Training
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.
-
CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval
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...
-
Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering
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.
-
MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
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...
-
ASARL: Autonomous Social-Aware Relevance Learning for QQ Search
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.
-
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
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-...
-
Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation
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...
-
JobMatchAI-An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI
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.
-
Negative Data Mining for Contrastive Learning in Dense Retrieval at IKEA.com
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.