{"total":97,"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":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235,"area":null},{"id":"2108.05540","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval","created":"2021-08-12","cited_by_count":203,"area":null},{"id":"2110.07367","title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","created":"2021-10-14","cited_by_count":176,"area":null},{"id":"2104.08253","title":"Condenser: a Pre-training Architecture for Dense Retrieval","created":"2021-04-16","cited_by_count":162,"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":"2110.03611","title":"Adversarial Retriever-Ranker for dense text retrieval","created":"2021-10-07","cited_by_count":83,"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":"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":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","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":"2212.02027","title":"Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer","created":"2022-12-05","cited_by_count":45,"area":null},{"id":"2203.08372","title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","created":"2022-03-16","cited_by_count":41,"area":null},{"id":"2205.09153","title":"ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval","created":"2022-05-18","cited_by_count":41,"area":null},{"id":"2206.08063","title":"Towards Robust Ranker for Text Retrieval","created":"2022-06-16","cited_by_count":37,"area":null},{"id":"2209.06506","title":"Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models","created":"2022-09-14","cited_by_count":37,"area":null},{"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":"2207.03637","title":"OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering","created":"2022-07-08","cited_by_count":29,"area":null},{"id":"2203.03367","title":"Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval","created":"2022-03-07","cited_by_count":27,"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":"2203.06169","title":"LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval","created":"2022-03-11","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":"2210.11773","title":"SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval","created":"2022-10-21","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":"2210.15859","title":"You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM","created":"2022-10-28","cited_by_count":18,"area":null},{"id":"2310.14587","title":"Large Search Model: Redefining Search Stack in the Era of LLMs","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2204.02292","title":"Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval","created":"2022-04-05","cited_by_count":17,"area":null},{"id":"2206.02873","title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","created":"2022-06-06","cited_by_count":17,"area":null},{"id":"2208.07670","title":"ConTextual Masked Auto-Encoder for Dense Passage Retrieval","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2203.10232","title":"DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine","created":"2022-03-19","cited_by_count":15,"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":"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":"2211.01267","title":"Multi-Vector Retrieval as Sparse Alignment","created":"2022-11-02","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":"2204.11673","title":"Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking","created":"2022-04-25","cited_by_count":10,"area":null},{"id":"2110.09455","title":"TLDR: Twin Learning for Dimensionality Reduction","created":"2021-10-18","cited_by_count":9,"area":null},{"id":"2204.11458","title":"ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference","created":"2022-04-25","cited_by_count":9,"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":"2407.17827","title":"Unified Lexical Representation for Interpretable Visual-Language Alignment","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2209.00218","title":"Isotropic Representation Can Improve Dense Retrieval","created":"2022-09-01","cited_by_count":8,"area":null},{"id":"2312.05417","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","created":"2023-12-09","cited_by_count":8,"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":"2212.07841","title":"MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers","created":"2022-12-15","cited_by_count":7,"area":null},{"id":"2302.09473","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","created":"2023-02-19","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":"2210.02068","title":"Nonparametric Decoding for Generative Retrieval","created":"2022-10-05","cited_by_count":6,"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":"2302.03222","title":"Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support","created":"2023-02-07","cited_by_count":6,"area":null},{"id":"2406.17968","title":"Efficient Document Ranking with Learnable Late Interactions","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2204.00958","title":"Long-tailed Extreme Multi-label Text Classification with Generated Pseudo Label Descriptions","created":"2022-04-02","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":"2505.13757","title":"CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval","created":"2025-05-19","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":"2212.09114","title":"CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion","created":"2022-12-18","cited_by_count":4,"area":null},{"id":"2409.17745","title":"Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model","created":"2024-09-26","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":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"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":"2305.13197","title":"Challenging Decoder helps in Masked Auto-Encoder Pre-training for Dense Passage Retrieval","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2305.14087","title":"BM25 Query Augmentation Learned End-to-End","created":"2023-05-23","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":"2202.13100","title":"SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization","created":"2022-02-26","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":"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":"2302.06589","title":"Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction","created":"2023-02-13","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":"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":"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":"2207.04656","title":"Topic-Grained Text Representation-based Model for Document Retrieval","created":"2022-07-11","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":"2303.05153","title":"Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?","created":"2023-03-09","cited_by_count":0,"area":null},{"id":"2308.02926","title":"Towards Consistency Filtering-Free Unsupervised Learning for Dense Retrieval","created":"2023-08-05","cited_by_count":0,"area":null},{"id":"2311.07204","title":"On Elastic Language Models","created":"2023-11-13","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":"2506.21913","title":"HyReC: Exploring Hybrid-based Retriever for Chinese","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2510.16393","title":"Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2510.22479","title":"Contextual Tokenization for Graph Inverted Indices","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2604.21511","title":"From Tokens to Concepts: Leveraging SAE for SPLADE","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.24914","title":"MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation","created":"2026-05-24","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":"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":"2607.01601","title":"SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.23307","title":"Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.31498","title":"Retail Product Search: A Practical Approach at Target","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}