{"total":40,"rows":[{"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":"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":"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":"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":"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":"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":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"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":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2104.07198","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2407.21488","title":"Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval","created":"2024-07-31","cited_by_count":7,"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":"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":"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":"2407.09395","title":"Deep Bag-of-Words Model: An Efficient and Interpretable Relevance Architecture for Chinese E-Commerce","created":"2024-07-12","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":"2201.11367","title":"Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation","created":"2022-01-27","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":"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":"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":"2402.16769","title":"Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2406.08215","title":"SumHiS: Extractive Summarization Exploiting Hidden Structure","created":"2024-06-12","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":"2505.12260","title":"LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference","created":"2025-05-18","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":"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":"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":"2406.01233","title":"Multi-word Term Embeddings Improve Lexical Product Retrieval","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2411.12921","title":"A Comparative Study of Text Retrieval Models on DaReCzech","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2505.24219","title":"ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.21913","title":"HyReC: Exploring Hybrid-based Retriever for Chinese","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2601.05262","title":"LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever","created":"2025-10-31","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}],"next_cursor":null}