{"total":168,"rows":[{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252,"area":null},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303,"area":null},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247,"area":null},{"id":"2102.07033","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","created":"2021-02-13","cited_by_count":200,"area":null},{"id":"2102.07662","title":"Overview of the TREC 2020 deep learning track","created":"2021-02-15","cited_by_count":196,"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":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","cited_by_count":149,"area":null},{"id":"2305.13117","title":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","created":"2023-05-22","cited_by_count":144,"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":"2112.07577","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","created":"2021-12-14","cited_by_count":119,"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":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107,"area":null},{"id":"2503.07891","title":"Gemini Embedding: Generalizable Embeddings from Gemini","created":"2025-03-10","cited_by_count":94,"area":null},{"id":"2110.03611","title":"Adversarial Retriever-Ranker for dense text retrieval","created":"2021-10-07","cited_by_count":83,"area":null},{"id":"2101.05667","title":"The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models","created":"2021-01-14","cited_by_count":81,"area":null},{"id":"2408.01875","title":"Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval","created":"2024-08-03","cited_by_count":52,"area":null},{"id":"2108.06027","title":"PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval","created":"2021-08-13","cited_by_count":50,"area":null},{"id":"2305.11841","title":"How Does Generative Retrieval Scale to Millions of Passages?","created":"2023-05-19","cited_by_count":48,"area":null},{"id":"2104.13615","title":"MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories","created":"2021-04-28","cited_by_count":46,"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":"2204.05511","title":"GERE: Generative Evidence Retrieval for Fact Verification","created":"2022-04-12","cited_by_count":38,"area":null},{"id":"2206.08063","title":"Towards Robust Ranker for Text Retrieval","created":"2022-06-16","cited_by_count":37,"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":"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":"2309.08541","title":"When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets","created":"2023-09-15","cited_by_count":26,"area":null},{"id":"2106.14726","title":"Keyphrase Generation for Scientific Document Retrieval","created":"2021-06-28","cited_by_count":23,"area":null},{"id":"2109.05897","title":"Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","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":"2210.15718","title":"QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation","created":"2022-10-27","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":"2205.11194","title":"UnifieR: A Unified Retriever for Large-Scale Retrieval","created":"2022-05-23","cited_by_count":19,"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":"2310.20158","title":"GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval","created":"2023-10-31","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":"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":"2104.14133","title":"Text-to-Text Multi-view Learning for Passage Re-ranking","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2308.16753","title":"Context Aware Query Rewriting for Text Rankers using LLM","created":"2023-08-31","cited_by_count":14,"area":null},{"id":"2404.16260","title":"OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search","created":"2024-04-25","cited_by_count":13,"area":null},{"id":"2502.15957","title":"R$^3$Mem: Bridging Memory Retention and Retrieval via Reversible Compression","created":"2025-02-21","cited_by_count":12,"area":null},{"id":"2504.07439","title":"LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking","created":"2025-04-10","cited_by_count":12,"area":null},{"id":"2103.12440","title":"Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness","created":"2021-03-23","cited_by_count":11,"area":null},{"id":"2305.07402","title":"Synergistic Interplay between Search and Large Language Models for Information Retrieval","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2310.08232","title":"Language Models are Universal Embedders","created":"2023-10-12","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":"2410.18634","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2105.09816","title":"Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking","created":"2021-05-20","cited_by_count":10,"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":"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":"2305.11944","title":"Exploring the Viability of Synthetic Query Generation for Relevance Prediction","created":"2023-05-19","cited_by_count":9,"area":null},{"id":"2403.05217","title":"Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering","created":"2024-03-08","cited_by_count":8,"area":null},{"id":"2410.16148","title":"PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters","created":"2024-10-21","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":"2102.09206","title":"Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder","created":"2021-02-18","cited_by_count":7,"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":"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":"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":"2308.08285","title":"Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval","created":"2023-08-16","cited_by_count":7,"area":null},{"id":"2404.08535","title":"Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking","created":"2024-04-12","cited_by_count":7,"area":null},{"id":"2502.11181","title":"Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation","created":"2025-02-16","cited_by_count":7,"area":null},{"id":"2503.01256","title":"Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners","created":"2025-03-03","cited_by_count":7,"area":null},{"id":"2211.12124","title":"A Large-Scale Dataset for Biomedical Keyphrase Generation","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2303.11648","title":"Improving Content Retrievability in Search with Controllable Query Generation","created":"2023-03-21","cited_by_count":6,"area":null},{"id":"2311.11226","title":"An Interactive Query Generation Assistant using LLM-based Prompt Modification and User Feedback","created":"2023-11-19","cited_by_count":6,"area":null},{"id":"2505.12950","title":"GuRE:Generative Query REwriter for Legal Passage Retrieval","created":"2025-05-19","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":"2603.17787","title":"Governed Memory: A Production Architecture for Multi-Agent Workflows","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2606.05894","title":"EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2310.04407","title":"Policy-Gradient Training of Language Models for Ranking","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2401.05939","title":"DREQ: Document Re-Ranking Using Entity-based Query Understanding","created":"2024-01-11","cited_by_count":5,"area":null},{"id":"2402.07262","title":"Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi","created":"2024-02-11","cited_by_count":5,"area":null},{"id":"2405.17658","title":"Generative Query Reformulation Using Ensemble Prompting, Document Fusion, and Relevance Feedback","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2406.16013","title":"Database-Augmented Query Representation for Information Retrieval","created":"2024-06-23","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":"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":"2212.09114","title":"CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion","created":"2022-12-18","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":"2406.01197","title":"A Survey of Generative Information Retrieval","created":"2024-06-03","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":"2102.06815","title":"Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2112.13946","title":"The University of Texas at Dallas HLTRI's Participation in EPIC-QA: Searching for Entailed Questions Revealing Novel Answer Nuggets","created":"2021-12-28","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":"2305.15098","title":"Referral Augmentation for Zero-Shot Information Retrieval","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2306.07875","title":"ReadProbe: A Demo of Retrieval-Enhanced Large Language Models to Support Lateral Reading","created":"2023-06-13","cited_by_count":3,"area":null},{"id":"2311.01666","title":"Plot Retrieval as an Assessment of Abstract Semantic Association","created":"2023-11-03","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":"2503.03417","title":"When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2508.21632","title":"QZhou-Embedding Technical Report","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2509.00842","title":"Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2511.08029","title":"BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2110.07701","title":"Exposing Query Identification for Search Transparency","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2207.01262","title":"Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2211.03988","title":"Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2302.01148","title":"Combining Deep Neural Reranking and Unsupervised Extraction for Multi-Query Focused Summarization","created":"2023-02-02","cited_by_count":2,"area":null}],"next_cursor":"100"}