{"total":127,"rows":[{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216,"area":null},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476,"area":null},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456,"area":null},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361,"area":null},{"id":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235,"area":null},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204,"area":null},{"id":"2305.13661","title":"On the Risk of Misinformation Pollution with Large Language Models","created":"2023-05-23","cited_by_count":128,"area":null},{"id":"2302.07452","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","created":"2023-02-15","cited_by_count":118,"area":null},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113,"area":null},{"id":"2205.09707","title":"PLAID: An Efficient Engine for Late Interaction Retrieval","created":"2022-05-19","cited_by_count":101,"area":null},{"id":"2312.15503","title":"Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval","created":"2023-12-24","cited_by_count":78,"area":null},{"id":"2403.06789","title":"SPLADE-v3: New baselines for SPLADE","created":"2024-03-11","cited_by_count":72,"area":null},{"id":"2309.15088","title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models","created":"2023-09-26","cited_by_count":70,"area":null},{"id":"2206.08063","title":"Towards Robust Ranker for Text Retrieval","created":"2022-06-16","cited_by_count":37,"area":null},{"id":"2303.00807","title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","created":"2023-03-01","cited_by_count":37,"area":null},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2304.01982","title":"Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","created":"2023-04-04","cited_by_count":31,"area":null},{"id":"2310.07712","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","created":"2023-10-11","cited_by_count":31,"area":"lr"},{"id":"2304.04358","title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","created":"2023-04-10","cited_by_count":29,"area":null},{"id":"2305.07614","title":"NevIR: Negation in Neural Information Retrieval","created":"2023-05-12","cited_by_count":29,"area":null},{"id":"2204.02363","title":"Towards Best Practices for Training Multilingual Dense Retrieval Models","created":"2022-04-05","cited_by_count":26,"area":null},{"id":"2207.03834","title":"An Efficiency Study for SPLADE Models","created":"2022-07-08","cited_by_count":26,"area":null},{"id":"2309.08541","title":"When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets","created":"2023-09-15","cited_by_count":26,"area":null},{"id":"2110.01529","title":"A Proposed Conceptual Framework for a Representational Approach to Information Retrieval","created":"2021-10-04","cited_by_count":24,"area":null},{"id":"2301.13081","title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens","created":"2023-01-30","cited_by_count":23,"area":null},{"id":"2203.13088","title":"Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction","created":"2022-03-24","cited_by_count":21,"area":null},{"id":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","cited_by_count":21,"area":null},{"id":"2212.06121","title":"In Defense of Cross-Encoders for Zero-Shot Retrieval","created":"2022-12-12","cited_by_count":21,"area":null},{"id":"2404.06809","title":"Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation","created":"2024-04-10","cited_by_count":21,"area":"rag"},{"id":"2205.11194","title":"UnifieR: A Unified Retriever for Large-Scale Retrieval","created":"2022-05-23","cited_by_count":19,"area":null},{"id":"2211.10411","title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval","created":"2022-11-18","cited_by_count":19,"area":null},{"id":"2404.14600","title":"Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17,"area":"lr"},{"id":"2112.06540","title":"A Study on Token Pruning for ColBERT","created":"2021-12-13","cited_by_count":15,"area":"inference"},{"id":"2208.13661","title":"LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval","created":"2022-08-29","cited_by_count":15,"area":null},{"id":"2306.07471","title":"Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard","created":"2023-06-13","cited_by_count":15,"area":null},{"id":"2402.14151","title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives","created":"2024-02-21","cited_by_count":15,"area":null},{"id":"2402.13350","title":"PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods","created":"2024-02-20","cited_by_count":14,"area":null},{"id":"2305.02564","title":"RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2211.01267","title":"Multi-Vector Retrieval as Sparse Alignment","created":"2022-11-02","cited_by_count":12,"area":null},{"id":"2310.04678","title":"DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries","created":"2023-10-07","cited_by_count":11,"area":null},{"id":"2311.04694","title":"Evaluating Generative Ad Hoc Information Retrieval","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2112.05662","title":"Match Your Words! A Study of Lexical Matching in Neural Information Retrieval","created":"2021-12-10","cited_by_count":10,"area":null},{"id":"2301.10576","title":"A Study on FGSM Adversarial Training for Neural Retrieval","created":"2023-01-25","cited_by_count":10,"area":null},{"id":"2212.09598","title":"Query-as-context Pre-training for Dense Passage Retrieval","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2305.13915","title":"DAPR: A Benchmark on Document-Aware Passage Retrieval","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2402.16714","title":"Quantum Transformer: Accelerating model inference via quantum linear algebra","created":"2024-02-26","cited_by_count":9,"area":null},{"id":"2312.05417","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2508.08137","title":"MuaLLM: A Multimodal Large Language Model Agent for Circuit Design Assistance with Hybrid Contextual Retrieval-Augmented Generation","created":"2025-08-11","cited_by_count":8,"area":"mllm"},{"id":"2509.10697","title":"A Survey on Retrieval And Structuring Augmented Generation with Large Language Models","created":"2025-09-12","cited_by_count":8,"area":null},{"id":"2304.10195","title":"CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2209.15469","title":"Zero-Shot Retrieval with Search Agents and Hybrid Environments","created":"2022-09-30","cited_by_count":6,"area":"agents"},{"id":"2311.02834","title":"CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval","created":"2023-11-06","cited_by_count":6,"area":"moe"},{"id":"2505.07793","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","created":"2025-05-12","cited_by_count":6,"area":"ssm"},{"id":"2507.08336","title":"Distillation versus Contrastive Learning: How to Train Your Rerankers","created":"2025-07-11","cited_by_count":6,"area":"distill"},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2604.18584","title":"MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","created":"2026-04-20","cited_by_count":6,"area":"lr"},{"id":"2112.09628","title":"Sparsifying Sparse Representations for Passage Retrieval by Top-$k$ Masking","created":"2021-12-17","cited_by_count":5,"area":null},{"id":"2212.07699","title":"Retrieval-based Disentangled Representation Learning with Natural Language Supervision","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2304.03158","title":"CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2310.04407","title":"Policy-Gradient Training of Language Models for Ranking","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2601.01684","title":"LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum","created":"2026-01-04","cited_by_count":5,"area":null},{"id":"2212.10192","title":"Adam: Dense Retrieval Distillation with Adaptive Dark Examples","created":"2022-12-20","cited_by_count":4,"area":"distill"},{"id":"2311.15564","title":"Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval","created":"2023-11-27","cited_by_count":4,"area":null},{"id":"2406.17158","title":"DEXTER: A Benchmark for open-domain Complex Question Answering using LLMs","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2508.01405","title":"Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search","created":"2025-08-02","cited_by_count":4,"area":"rag"},{"id":"2509.16621","title":"The Role of Vocabularies in Learning Sparse Representations for Ranking","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2604.03676","title":"Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead","created":"2026-04-04","cited_by_count":4,"area":"lr"},{"id":"2607.18785","title":"SkillSight: Calibrating Generic Content Bias for Skill Retrieval","created":"2026-07-21","cited_by_count":4,"area":"agents"},{"id":"2305.14087","title":"BM25 Query Augmentation Learned End-to-End","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2409.05677","title":"RIRAG: Regulatory Information Retrieval and Answer Generation","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2412.08985","title":"KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?","created":"2024-12-12","cited_by_count":3,"area":"rag"},{"id":"2510.20609","title":"Practical Code RAG at Scale: Task-Aware Retrieval Design Choices under Compute Budgets","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2207.01262","title":"Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2210.05521","title":"Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2211.03988","title":"Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2211.08769","title":"RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2305.14499","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2307.10488","title":"SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval","created":"2023-07-19","cited_by_count":2,"area":null},{"id":"2504.01101","title":"Uncovering the Limitations of Query Performance Prediction: Failures, Insights, and Implications for Selective Query Processing","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2603.22300","title":"Scaling Attention via Feature Sparsity","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2607.04605","title":"Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval","created":"2026-07-06","cited_by_count":2,"area":"inference"},{"id":"2608.02583","title":"UEmbed: Unified Sparse and Dense Multimodal Embeddings","created":"2026-08-03","cited_by_count":2,"area":"rag"},{"id":"2210.12565","title":"A Visual Tour Of Current Challenges In Multimodal Language Models","created":"2022-10-22","cited_by_count":1,"area":"mllm"},{"id":"2309.06131","title":"Annotating Data for Fine-Tuning a Neural Ranker? Current Active Learning Strategies are not Better than Random Selection","created":"2023-09-12","cited_by_count":1,"area":null},{"id":"2311.09765","title":"Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense Encoders","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2405.07263","title":"Span-Aggregatable, Contextualized Word Embeddings for Effective Phrase Mining","created":"2024-05-12","cited_by_count":1,"area":null},{"id":"2505.04365","title":"CDE-Mapper: Using Retrieval-Augmented Language Models for Linking Clinical Data Elements to Controlled Vocabularies","created":"2025-05-07","cited_by_count":1,"area":"rag"},{"id":"2509.24815","title":"Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2511.05301","title":"QueStER: Query Specification for Generative keyword-based Retrieval","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2511.19324","title":"What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2511.22263","title":"Efficiency and Effectiveness of SPLADE Models on Billion-Scale Web Document Title","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2604.22436","title":"AgentSearchBench: A Benchmark for AI Agent Search in the Wild","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.30120","title":"No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2609.03874","title":"STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation","created":"2026-09-03","cited_by_count":1,"area":"rag"},{"id":"2204.07233","title":"How Different are Pre-trained Transformers for Text Ranking?","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2204.10558","title":"Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2306.09657","title":"Online Distillation for Pseudo-Relevance Feedback","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2308.12039","title":"Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track","created":"2023-08-23","cited_by_count":0,"area":null}],"next_cursor":"100"}