{"total":206,"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":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","cited_by_count":149,"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":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2403.06789","title":"SPLADE-v3: New baselines for SPLADE","created":"2024-03-11","cited_by_count":72,"area":null},{"id":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"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":"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":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2212.10380","title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2207.03834","title":"An Efficiency Study for SPLADE Models","created":"2022-07-08","cited_by_count":26,"area":null},{"id":"2408.16672","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever","created":"2024-08-29","cited_by_count":25,"area":null},{"id":"2409.14683","title":"Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling","created":"2024-09-23","cited_by_count":25,"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":"2410.15576","title":"A Survey of Conversational Search","created":"2024-10-21","cited_by_count":22,"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":"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":"2311.03057","title":"GLEN: Generative Retrieval via Lexical Index Learning","created":"2023-11-06","cited_by_count":17,"area":null},{"id":"2402.07092","title":"Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation","created":"2024-02-11","cited_by_count":17,"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":"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":"2406.06575","title":"Ask-EDA: A Design Assistant Empowered by LLM, Hybrid RAG and Abbreviation De-hallucination","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2407.01965","title":"AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2211.01267","title":"Multi-Vector Retrieval as Sparse Alignment","created":"2022-11-02","cited_by_count":12,"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":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2305.11052","title":"BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval","created":"2023-05-18","cited_by_count":11,"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":"2311.04694","title":"Evaluating Generative Ad Hoc Information Retrieval","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2403.04160","title":"Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2501.06582","title":"ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting","created":"2025-01-11","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":"2212.09598","title":"Query-as-context Pre-training for Dense Passage Retrieval","created":"2022-12-19","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":"2407.17827","title":"Unified Lexical Representation for Interpretable Visual-Language Alignment","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2504.05181","title":"Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval","created":"2025-04-07","cited_by_count":9,"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":"2404.00684","title":"Generative Retrieval as Multi-Vector Dense Retrieval","created":"2024-03-31","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":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"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":"2510.05396","title":"Scalable In-context Ranking with Generative Models","created":"2025-10-06","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":"2307.16779","title":"Lexically-Accelerated Dense Retrieval","created":"2023-07-31","cited_by_count":7,"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":"2403.04311","title":"Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2502.05364","title":"Hypencoder: Hypernetworks for Information Retrieval","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2506.01673","title":"GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2301.11309","title":"SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2302.03754","title":"Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories","created":"2023-02-07","cited_by_count":6,"area":null},{"id":"2404.05825","title":"LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2406.04298","title":"Measuring and Addressing Indexical Bias in Information Retrieval","created":"2024-06-06","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":"2509.07253","title":"Benchmarking Information Retrieval Models on Complex Retrieval Tasks","created":"2025-09-08","cited_by_count":6,"area":null},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","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":"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":"2408.07249","title":"Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2503.19868","title":"GENIUS: A Generative Framework for Universal Multimodal Search","created":"2025-03-25","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":"2201.03356","title":"Continual Learning of Long Topic Sequences in Neural Information Retrieval","created":"2022-01-10","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":"2212.01340","title":"Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2403.20222","title":"Shallow Cross-Encoders for Low-Latency Retrieval","created":"2024-03-29","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":"2411.14739","title":"IRLab@iKAT24: Learned Sparse Retrieval with Multi-aspect LLM Query Generation for Conversational Search","created":"2024-11-22","cited_by_count":4,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2202.07474","title":"Do Lessons from Metric Learning Generalize to Image-Caption Retrieval?","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2305.15098","title":"Referral Augmentation for Zero-Shot Information Retrieval","created":"2023-05-24","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":"2311.15563","title":"Noisy Self-Training with Synthetic Queries for Dense Retrieval","created":"2023-11-27","cited_by_count":3,"area":null},{"id":"2401.11248","title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval","created":"2024-01-20","cited_by_count":3,"area":null},{"id":"2405.00977","title":"Distillation for Multilingual Information Retrieval","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2411.04129","title":"AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2412.04637","title":"Semantic Retrieval at Walmart","created":"2024-12-05","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":"2505.19356","title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2602.16932","title":"RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution","created":"2026-02-18","cited_by_count":3,"area":null},{"id":"2301.10521","title":"ExaRanker: Explanation-Augmented Neural Ranker","created":"2023-01-25","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":"2308.15711","title":"Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2405.13173","title":"Efficient and Interpretable Information Retrieval for Product Question Answering with Heterogeneous Data","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2405.20654","title":"Passage-specific Prompt Tuning for Passage Reranking in Question Answering with Large Language Models","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2503.08379","title":"JurisTCU: A Brazilian Portuguese Information Retrieval Dataset with Query Relevance Judgments","created":"2025-03-11","cited_by_count":2,"area":null}],"next_cursor":"100"}