{"list":"other","total":65,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2403.14403","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","created":"2024-03-21","cited_by_count":451},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2010.10144","title":"Keystroke Dynamics as Part of Lifelogging","created":"2020-10-20","cited_by_count":334},{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302},{"id":"2107.05720","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","created":"2021-07-12","cited_by_count":286},{"id":"2401.14887","title":"The Power of Noise: Redefining Retrieval for RAG Systems","created":"2024-01-26","cited_by_count":281},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2012.04584","title":"Distilling Knowledge from Reader to Retriever for Question Answering","created":"2020-12-08","cited_by_count":226},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"2505.04588","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","created":"2025-05-07","cited_by_count":208},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165},{"id":"2404.00610","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","created":"2024-03-31","cited_by_count":147},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104},{"id":"2402.10828","title":"RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model","created":"2024-02-16","cited_by_count":92},{"id":"2401.10225","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","created":"2024-01-18","cited_by_count":90},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77},{"id":"2401.06954","title":"Bridging the Preference Gap between Retrievers and LLMs","created":"2024-01-13","cited_by_count":69},{"id":"2508.01780","title":"LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?","created":"2025-08-03","cited_by_count":48},{"id":"2509.13312","title":"WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research","created":"2025-09-16","cited_by_count":46},{"id":"2010.00768","title":"SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval","created":"2020-10-02","cited_by_count":45},{"id":"2404.03302","title":"How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?","created":"2024-04-04","cited_by_count":44},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44},{"id":"2406.19215","title":"SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation","created":"2024-06-27","cited_by_count":40},{"id":"2502.12342","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark","created":"2025-02-17","cited_by_count":35},{"id":"2501.12835","title":"Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home","created":"2025-01-22","cited_by_count":33},{"id":"2402.17497","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","created":"2024-02-27","cited_by_count":28},{"id":"2502.16101","title":"Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals","created":"2025-02-22","cited_by_count":28},{"id":"2410.23041","title":"Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval","created":"2024-10-30","cited_by_count":26},{"id":"2407.09893","title":"Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks","created":"2024-07-13","cited_by_count":23},{"id":"2208.14754","title":"LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval","created":"2022-08-31","cited_by_count":18},{"id":"2203.06942","title":"Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering","created":"2022-03-14","cited_by_count":15},{"id":"2211.02405","title":"Explainable Information Retrieval: A Survey","created":"2022-11-04","cited_by_count":15},{"id":"2409.11279","title":"P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task","created":"2024-09-17","cited_by_count":15},{"id":"2407.00072","title":"Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback","created":"2024-06-21","cited_by_count":8},{"id":"2408.11381","title":"RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation","created":"2024-08-21","cited_by_count":8},{"id":"2408.08444","title":"W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering","created":"2024-08-15","cited_by_count":6},{"id":"2212.07699","title":"Retrieval-based Disentangled Representation Learning with Natural Language Supervision","created":"2022-12-15","cited_by_count":5}],"next_cursor":null}