{"total":69,"rows":[{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073,"area":"distill"},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476,"area":null},{"id":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","cited_by_count":149,"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":"2205.04733","title":"From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective","created":"2022-05-10","cited_by_count":98,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2110.06918","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","created":"2021-10-13","cited_by_count":60,"area":null},{"id":"2206.10128","title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","created":"2022-06-21","cited_by_count":48,"area":null},{"id":"2310.13243","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","created":"2023-10-20","cited_by_count":44,"area":null},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"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":"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":"2212.06121","title":"In Defense of Cross-Encoders for Zero-Shot Retrieval","created":"2022-12-12","cited_by_count":21,"area":null},{"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":"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":"2402.17535","title":"Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control","created":"2024-02-27","cited_by_count":12,"area":null},{"id":"2410.01242","title":"RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance","created":"2024-10-02","cited_by_count":12,"area":"agents"},{"id":"2309.02233","title":"Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering","created":"2023-09-05","cited_by_count":11,"area":null},{"id":"2510.00671","title":"Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector","created":"2025-10-01","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":"2408.11119","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2506.00041","title":"Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval","created":"2025-05-28","cited_by_count":8,"area":"mechinterp"},{"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":"2402.15059","title":"ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2305.18952","title":"Exploring the Practicality of Generative Retrieval on Dynamic Corpora","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2501.09749","title":"Enhancing Lexicon-Based Text Embeddings with Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2506.04760","title":"Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion","created":"2025-06-05","cited_by_count":6,"area":null},{"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":"2210.07093","title":"Query Expansion Using Contextual Clue Sampling with Language Models","created":"2022-10-13","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":"2208.05753","title":"Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval","created":"2022-08-11","cited_by_count":4,"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":"2304.01019","title":"Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval","created":"2023-04-03","cited_by_count":4,"area":null},{"id":"2403.05975","title":"Measuring Bias in a Ranked List using Term-based Representations","created":"2024-03-09","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":"2301.10444","title":"An Experimental Study on Pretraining Transformers from Scratch for IR","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2305.18494","title":"Adapting Learned Sparse Retrieval for Long Documents","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2406.03592","title":"Measuring Retrieval Complexity in Question Answering Systems","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2505.15070","title":"An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doc","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2508.16707","title":"Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval","created":"2025-08-22","cited_by_count":3,"area":"mllm"},{"id":"2509.01088","title":"Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation","created":"2025-09-01","cited_by_count":3,"area":"lr"},{"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":"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":"2603.05781","title":"Visual Words Meet BM25: Sparse Auto-Encoder Visual Word Scoring for Image Retrieval","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2605.25092","title":"AgentIR: A Workload-Adaptive Cascade Retrieval Substrate for Long-Term Conversational Memory","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2609.00638","title":"It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning","created":"2026-09-01","cited_by_count":2,"area":"lr"},{"id":"2204.11545","title":"LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2205.09638","title":"Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2210.05145","title":"Retrieval Augmentation for T5 Re-ranker using External Sources","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2301.03765","title":"Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding","created":"2023-01-10","cited_by_count":1,"area":null},{"id":"2402.12663","title":"SoftQE: Learned Representations of Queries Expanded by LLMs","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2505.03676","title":"Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrieval","created":"2025-05-06","cited_by_count":1,"area":null},{"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":"2605.03675","title":"MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents","created":"2026-05-05","cited_by_count":1,"area":"agents"},{"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":"2210.10584","title":"Enhanced vectors for top-k document retrieval in Question Answering","created":"2022-10-08","cited_by_count":0,"area":null},{"id":"2404.12152","title":"FecTek: Enhancing Term Weight in Lexicon-Based Retrieval with Feature Context and Term-level Knowledge","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2405.01924","title":"Semi-Parametric Retrieval via Binary Bag-of-Tokens Index","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2511.20623","title":"Copyright Detection in Large Language Models: An Ethical Approach to Generative AI Development","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.13074","title":"A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2605.30917","title":"Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.00004","title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2608.16309","title":"Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.03901","title":"Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US Universities","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}