ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
2020/04/27 by Omar Khattab, Matei Zaharia, Khattab, Omar +1 · 1 voice · 306 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Web Data Mining and Analysis #cs.CL #cs.IR
paper · pdf · doi:10.48550/arxiv.2004.12832
Accepted at SIGIR 2020
arxiv published 2020/04/27 · arxiv created 2020/06/04 · arxiv updated 2020/06/05
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.
Citations
Cited by
- Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration
- Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework
- Towards a Relevance Posterior in Neural Information Access
- Do Current Retrievers Cover All the Evidence? A Controlled Study of Conjunctive Cross-Page Retrieval
- VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy
- Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering
- The Case Against Generation for Retrieval: Discriminative Language Models as Effective Retrievers
- SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
- RoboMME-Interference: Benchmarking Robot Memory Under Interference
- GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models
- JobMatchAI-An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI
- Structured Visualization Design Knowledge for Grounding Generative Reasoning and Situated Feedback
- A Large-Language-Model Framework for Automated Humanitarian Situation Reporting
- brat: Aligned Multi-View Embeddings for Brain MRI Analysis
- Exploration of Augmentation Strategies in Multi-modal Retrieval-Augmented Generation for the Biomedical Domain: A Case Study Evaluating Question Answering in Glycobiology
- Design and Evaluation of Cost-Aware PoQ for Decentralized LLM Inference
- The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models
- A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval
- Are Large Language Models Really Effective for Training-Free Cold-Start Recommendation?
- Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval
- Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context
- amc: The Automated Mission Classifier for Telescope Bibliographies
- Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly
- Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
- TopiCLEAR: Topic extraction by CLustering Embeddings with Adaptive dimensional Reduction
- MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
- M3DR: Towards Universal Multilingual Multimodal Document Retrieval
- Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
- Beyond Patch Aggregation: 3-Pass Pyramid Indexing for Vision-Enhanced Document Retrieval
- MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
- Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs
- MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction
- What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models
- ReMatch: Boosting Representation through Matching for Multimodal Retrieval
- CREST: Improving Interpretability and Effectiveness of Troubleshooting at Ericsson through Criterion-Specific Trouble Report Retrieval
- KRAL: Knowledge and Reasoning Augmented Learning for LLM-assisted Clinical Antimicrobial Therapy
- Incorporating Token Importance in Multi-Vector Retrieval
- TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval
- CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search
- Attention Grounded Enhancement for Visual Document Retrieval
- RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
- MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues
- Reinforcing Trustworthiness in Multimodal Emotional Support Systems
- TurkEmbed: Turkish Embedding Model on NLI & STS Tasks
- Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker
- TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task
- Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights
- An Efficient Proximity Graph-based Approach to Table Union Search
- Query Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval
- Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG
- E-CARE: An Efficient LLM-based Commonsense-Augmented Framework for E-Commerce
- Cache Mechanism for Agent RAG Systems
- Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
- ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
- All-in-one Graph-based Indexing for Hybrid Search on GPUs
- LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026
- BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
- MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
- Secure Retrieval-Augmented Generation against Poisoning Attacks
- Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
- Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
- Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades
- SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications
- Charting the Design Space of Neural Graph Representations for Subgraph Matching
- Contextual Tokenization for Graph Inverted Indices
- Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy
- GRATING: Low-Latency and Memory-Efficient Semantic Selection on Device
- Multimedia-Aware Question Answering: A Review of Retrieval and Cross-Modal Reasoning Architectures
- Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
- C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search
- Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering
- LLMs as Sparse Retrievers:A Framework for First-Stage Product Search
- OG-Rank: Learning to Rank Fast and Slow with Uncertainty and Reward-Trend Guided Adaptive Exploration
- Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce
- Exact Nearest-Neighbor Search on Energy-Efficient FPGA Devices
- Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
- BiMax: Bidirectional MaxSim Score for Document-Level Alignment
- Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report
- Hierarchical Semantic Retrieval with Cobweb
- Document Intelligence in the Era of Large Language Models: A Survey
- Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval
- Revisiting Query Variants: The Advantage of Retrieval Over Generation of Query Variants for Effective QPP
- CTRL-Rec: Controlling Recommender Systems With Natural Language
- Simple Projection Variants Improve ColBERT Performance
- REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking
- QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
- From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
- ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
- Stronger Re-identification Attacks through Reasoning and Aggregation
- MIRAGE: Runtime Scheduling for Multi-Vector Image Retrieval with Hierarchical Decomposition
- Multilingual Generative Retrieval via Cross-lingual Semantic Compression
- VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents
- LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
- Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
- Reproducing and Extending Causal Insights Into Term Frequency Computation in Neural Rankers
- Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
- Bridging Clinical Narratives and ACR Appropriateness Guidelines: A Multi-Agent RAG System for Medical Imaging Decisions
- ModernBERT + ColBERT: Enhancing biomedical RAG through an advanced re-ranking retriever
- UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG
- From Factoid Questions to Data Product Requests: Benchmarking Data Product Discovery over Tables and Text
- HLTCOE at TREC 2024 NeuCLIR Track
- UniDex: Rethinking Search Inverted Indexing with Unified Semantic Modeling
- DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning
- Investigating Multi-layer Representations for Dense Passage Retrieval
- Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models
- Does Generative Retrieval Overcome the Limitations of Dense Retrieval?
- QuantMind: A Context-Engineering Based Knowledge Framework for Quantitative Finance
- RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
- Learning Contextual Retrieval for Robust Conversational Search
- Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
- Retrieval from Within: An Intrinsic Capability of Attention-Based Models
- Demographically-Inspired Query Variants Using an LLM
- LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation
- Memory in Large Language Models: Mechanisms, Evaluation and Evolution
- Semantic Search for Information Retrieval
- Global Minimizers of Sigmoid Contrastive Loss
- MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
- Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever
- The Role of Vocabularies in Learning Sparse Representations for Ranking
- Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
- What's the Best Way to Retrieve Slides? A Comparative Study of Multimodal, Caption-Based, and Hybrid Retrieval Techniques
- Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs
- Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
- Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluation
- A Learnable Fully Interacted Two-Tower Model for Pre-Ranking System
- Red Dragon AI at TextGraphs 2021 Shared Task: Multi-Hop Inference Explanation Regeneration by Matching Expert Ratings
- Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation
- Graph-Enhanced Retrieval-Augmented Question Answering for E-Commerce Customer Support
- AI Answer Engine Citation Behavior An Empirical Analysis of the GEO16 Framework
- A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
- Vector embedding of multi-modal texts: a tool for discovery?
- Recurrence Meets Transformers for Universal Multimodal Retrieval
- Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey
- A Survey of Long-Document Retrieval in the PLM and LLM Era
- How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models
- OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
- IntenT5: Search Result Diversification using Causal Language Models
- HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
- Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering
- Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval
- A Survey on Open Dataset Search in the LLM Era: Retrospectives and Perspectives
- RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring
- T-Retrievability: A Topic-Focused Approach to Measure Fair Document Exposure in Information Retrieval
- SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval
- From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data
- NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Enhancing Document VQA Models via Retrieval-Augmented Generation
- CASPER: Concept-integrated Sparse Representation for Scientific Retrieval
- DeCAL Tokenwise Compression
- VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding
- AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning
- CLAP: Coreference-Linked Augmentation for Passage Retrieval
- Improving Table Retrieval with Question Generation from Partial Tables
- RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback
- RRRA: Resampling and Reranking through a Retriever Adapter
- LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay
- PyLate: Flexible Training and Retrieval for Late Interaction Models
- LLM-based IR-system for Bank Supervisors
- Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking
- Provably Secure Retrieval-Augmented Generation
- MHier-RAG: Multi-Modal RAG for Visual-Rich Document Question-Answering via Hierarchical and Multi-Granularity Reasoning
- SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval
- MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation
- Automating AI Failure Tracking: Semantic Association of Reports in AI Incident Database
- Enhanced Arabic Text Retrieval with Attentive Relevance Scoring
- Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval
- A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers
- ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval
- On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey
- Co-NAML-LSTUR: A Combined Model with Attentive Multi-View Learning and Long- and Short-term User Representations for News Recommendation
- Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving
- Code Clone Detection via an AlphaFold-Inspired Framework
- Closing the Modality Gap for Mixed Modality Search
- MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks
- Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language models
- Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation
- LLM-based Embedders for Prior Case Retrieval
- Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
- FutureSim: Replaying World Events to Evaluate Adaptive Agents
- Foundations of Vector Retrieval
- IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering
- Content-based 3D Image Retrieval and a ColBERT-inspired Re-ranking for Tumor Flagging and Staging
- Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
- Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings
- Extracting Document Relations from Search Corpus by Marginalizing over User Queries
- Smart Routing for Multimodal Video Retrieval: When to Search What
- Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging
- RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval
- Rethinking the Privacy of Text Embeddings: A Reproducibility Study of "Text Embeddings Reveal (Almost) As Much As Text"
- Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
- Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search
- KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented Generation
- STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking
- Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-training
- Should We Still Pretrain Encoders with Masked Language Modeling?
- Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation
- R1-Ranker: Teaching LLM Rankers to Reason
- jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
- When Fine-Tuning Fails: Lessons from MS MARCO Passage Ranking
- A GenAI System for Improved FAIR Independent Biological Database Integration
- HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrieval
- eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing
- Structured Attention Matters to Multimodal LLMs in Document Understanding
- Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering
- Evaluating the Robustness of Dense Retrievers in Interdisciplinary Domains
- SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
- How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval
- DoTA-RAG: Dynamic of Thought Aggregation RAG
- FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation
- TongSearch-QR: Reinforced Query Reasoning for Retrieval
- Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
- MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling
- Don't Pay Attention
- Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval
- MIRIAD: Augmenting LLMs with millions of medical query-response pairs
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval
- Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation
- Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
- BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search
- CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents
- Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning
- MGS3: A Multi-Granularity Self-Supervised Code Search Framework
- Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
- On the Scaling of Robustness and Effectiveness in Dense Retrieval
- CoRet: Improved Retriever for Code Editing
- Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models
- DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers
- Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
- Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents
- Real-time Spatial Retrieval Augmented Generation for Urban Environments
- Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
- POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
- Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval
- Modeling Ranking Properties with In-Context Learning
- Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs
- Disentangled Contrastive Learning for Zero-Shot Multilingual Dense Retrieval
- DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes
- CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
- MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries
- Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering
- After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in RAG
- Do RAG Systems Really Suffer From Positional Bias?
- VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval
- RaG-Tree: Combining R-Tree and HNSW for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search
- Rank-K: Test-Time Reasoning for Listwise Reranking
- Re-identification of De-identified Documents with Autoregressive Infilling
- Real-Time Hybrid Retrieval in Hyperbolic Space for Retrieval-Augmented Generation on Edge Devices
- Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation
- LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference
- Collaborative Memory Augmentation for Generative Recommendation
- ELITE: Embedding-Less retrieval with Iterative Text Exploration
- Select-And-Extract: A Lightweight Plugin for Retrieval-Augmented Generation
- Benchmarking LLMs on File System Design and Implementation
- SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering
- Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval
- H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases
- Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval
- Even Faster Algorithm for the Chamfer Distance
- Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction
- DocVXQA: Context-Aware Visual Explanations for Document Question Answering
- OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval
- MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
- Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval
- Neural Catalog: Scaling Species Recognition with Catalog of Life-Augmented Generation
- DepreSym: A Depression Symptom Annotated Corpus and the Role of Large Language Models as Assessors of Psychological Markers
- Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
- OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
- Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model
- Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method
- Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
- Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages
- Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
- Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?
- VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
- Evergreen: Efficient Claim Verification for Semantic Aggregates
- PROTOCOL: Late Interaction Retrieval for Protein Homolog Search
- MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
- flexvec: SQL Vector Retrieval with Programmatic Embedding Modulation
- Revisiting Text Ranking in Deep Research
- MINT: Multi-Vector Search Index Tuning
- Formal Verification of TurboQuant: Machine-Checked Proofs and Gap Closures
- All Eyes on the Ranker: Participatory Auditing to Surface Blind Spots in Ranked Search Results
- Semantic Search over 9 Million Mathematical Theorems
- Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
- AI for Mathematics: Progress, Challenges, and Prospects
- Coverage Matters: MarginMerge for Compressing Multi-Vector Visual Document Retrievers
- RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
- Towards Visual Text Grounding of Multimodal Large Language Model
- Recall Is Not Enough: A Reader-Context Diagnostic for Budget-Constrained Retrieval-Augmented Generation
- A Theoretical Framework for Risk Analysis of Stochastic Rankers
- Document Optimization for Black-Box Retrieval via Reinforcement Learning
- Splits! A Flexible Dataset and Evaluation Framework for Sociocultural Linguistic Investigation
- TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval
- CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents
- CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction
- ColBERT-serve: Efficient Multi-Stage Memory-Mapped Scoring
- Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answering
- Towards Lossless Token Pruning in Late-Interaction Retrieval Models
- BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks
- EXCISE: Query-Side Exclusion for Late-Interaction Retrieval
- Augmented Relevance Datasets with Fine-Tuned Small LLMs
- HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
- How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective
- Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
Discussions
Related