{"total":60,"rows":[{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476,"area":null},{"id":"2109.10086","title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","created":"2021-09-21","cited_by_count":127,"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":"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":"2106.14807","title":"A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques","created":"2021-06-28","cited_by_count":69,"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":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2207.03834","title":"An Efficiency Study for SPLADE Models","created":"2022-07-08","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":"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":"2403.00784","title":"Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges","created":"2024-02-18","cited_by_count":20,"area":null},{"id":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20,"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":"2305.16675","title":"Multiview Identifiers Enhanced Generative Retrieval","created":"2023-05-26","cited_by_count":16,"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":"2304.11943","title":"Constructing Tree-based Index for Efficient and Effective Dense Retrieval","created":"2023-04-24","cited_by_count":15,"area":null},{"id":"2504.01818","title":"Efficient Constant-Space Multi-Vector Retrieval","created":"2025-04-02","cited_by_count":12,"area":null},{"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":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","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":"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":"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":"2112.09628","title":"Sparsifying Sparse Representations for Passage Retrieval by Top-$k$ Masking","created":"2021-12-17","cited_by_count":5,"area":null},{"id":"2112.08766","title":"CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking","created":"2021-12-16","cited_by_count":4,"area":null},{"id":"2208.04232","title":"Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval","created":"2022-08-08","cited_by_count":4,"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":"2210.15133","title":"Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval","created":"2022-10-27","cited_by_count":4,"area":null},{"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":"2403.00801","title":"Self-Retrieval: End-to-End Information Retrieval with One Large Language Model","created":"2024-02-23","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":"2509.16621","title":"The Role of Vocabularies in Learning Sparse Representations for Ranking","created":"2025-09-20","cited_by_count":4,"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":"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":"2603.22008","title":"On the Challenges and Opportunities of Learned Sparse Retrieval for Code","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2202.13869","title":"Query Expansion and Entity Weighting for Query Reformulation Retrieval in Voice Assistant Systems","created":"2022-02-22","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":"2206.12993","title":"Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems","created":"2022-06-26","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":"2504.14839","title":"Exploring $\\ell_0$ Sparsification for Inference-free Sparse Retrievers","created":"2025-04-21","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":"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":"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":"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":"2511.05000","title":"Query Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2601.17500","title":"To Case or Not to Case: An Empirical Study in Learned Sparse Retrieval","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2605.29384","title":"Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies","created":"2026-05-28","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":"2606.05568","title":"ColBERTSaR: Sparsified ColBERT Index via Product Quantization","created":"2026-06-04","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}],"next_cursor":null}