{"total":93,"rows":[{"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,"area":"rag"},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702,"area":"rag"},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452,"area":"rag"},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256,"area":"rag"},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2305.18466","title":"Test-Time Training on Nearest Neighbors for Large Language Models","created":"2023-05-29","cited_by_count":88,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71,"area":null},{"id":"2201.12431","title":"Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval","created":"2022-01-28","cited_by_count":60,"area":null},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2403.10059","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","created":"2024-03-15","cited_by_count":55,"area":"rag"},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40,"area":null},{"id":"2205.14704","title":"Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning","created":"2022-05-29","cited_by_count":36,"area":"rag"},{"id":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2410.13509","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","created":"2024-10-17","cited_by_count":33,"area":"rag"},{"id":"2305.14888","title":"Privacy Implications of Retrieval-Based Language Models","created":"2023-05-24","cited_by_count":32,"area":null},{"id":"2502.12961","title":"Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger","created":"2025-02-18","cited_by_count":30,"area":"agents"},{"id":"2509.13237","title":"Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors","created":"2025-09-16","cited_by_count":30,"area":"lr"},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29,"area":null},{"id":"2301.02828","title":"Why do Nearest Neighbor Language Models Work?","created":"2023-01-07","cited_by_count":29,"area":"rag"},{"id":"2205.13792","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","created":"2022-05-27","cited_by_count":27,"area":"rag"},{"id":"2307.06962","title":"Copy Is All You Need","created":"2023-07-13","cited_by_count":27,"area":null},{"id":"2402.11626","title":"Metacognitive Retrieval-Augmented Large Language Models","created":"2024-02-18","cited_by_count":26,"area":"rag"},{"id":"2404.19543","title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","created":"2024-04-30","cited_by_count":25,"area":"rag"},{"id":"2405.19325","title":"Nearest Neighbor Speculative Decoding for LLM Generation and Attribution","created":"2024-05-29","cited_by_count":25,"area":"inference"},{"id":"2204.06175","title":"Efficient Cluster-Based k-Nearest-Neighbor Machine Translation","created":"2022-04-13","cited_by_count":24,"area":null},{"id":"2205.12230","title":"Chunk-based Nearest Neighbor Machine Translation","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2402.00707","title":"Non-Exchangeable Conformal Language Generation with Nearest Neighbors","created":"2024-02-01","cited_by_count":21,"area":null},{"id":"2401.14021","title":"Accelerating Retrieval-Augmented Language Model Serving with Speculation","created":"2024-01-25","cited_by_count":20,"area":"rag"},{"id":"2508.01832","title":"MLP Memory: A Retriever-Pretrained Memory for Large Language Models","created":"2025-08-03","cited_by_count":20,"area":"rag"},{"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":"2306.04123","title":"Retrosynthesis Prediction with Local Template Retrieval","created":"2023-06-07","cited_by_count":16,"area":null},{"id":"2508.09874","title":"Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models","created":"2025-08-13","cited_by_count":16,"area":null},{"id":"2302.10879","title":"$k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models","created":"2023-02-21","cited_by_count":14,"area":null},{"id":"2405.20834","title":"Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning","created":"2024-05-31","cited_by_count":14,"area":"lr"},{"id":"2409.17275","title":"On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains","created":"2024-09-12","cited_by_count":14,"area":"rag"},{"id":"2205.02355","title":"Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning","created":"2022-05-04","cited_by_count":13,"area":null},{"id":"2201.05575","title":"Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings","created":"2022-01-14","cited_by_count":12,"area":"lr"},{"id":"2205.11211","title":"Non-Parametric Domain Adaptation for End-to-End Speech Translation","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2302.12188","title":"Simple and Scalable Nearest Neighbor Machine Translation","created":"2023-02-23","cited_by_count":12,"area":null},{"id":"2303.01421","title":"Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory","created":"2023-03-02","cited_by_count":12,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2305.14625","title":"KNN-LM Does Not Improve Open-ended Text Generation","created":"2023-05-24","cited_by_count":10,"area":"rag"},{"id":"2404.01554","title":"FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completion","created":"2024-04-02","cited_by_count":9,"area":"rag"},{"id":"2504.01018","title":"Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization","created":"2025-04-01","cited_by_count":9,"area":"rag"},{"id":"2502.18817","title":"Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models","created":"2025-02-26","cited_by_count":8,"area":"rag"},{"id":"2204.12608","title":"Efficient Machine Translation Domain Adaptation","created":"2022-04-26","cited_by_count":7,"area":null},{"id":"2302.12563","title":"Retrieved Sequence Augmentation for Protein Representation Learning","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2404.02835","title":"Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison","created":"2024-04-03","cited_by_count":7,"area":"rag"},{"id":"2506.24106","title":"On the Predictive Power of Representation Dispersion in Language Models","created":"2025-06-30","cited_by_count":7,"area":null},{"id":"2602.11182","title":"MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2211.07828","title":"Adaptation Approaches for Nearest Neighbor Language Models","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2410.08481","title":"Generation with Dynamic Vocabulary","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2504.08761","title":"UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation","created":"2025-03-31","cited_by_count":6,"area":"rag"},{"id":"2302.12211","title":"Federated Nearest Neighbor Machine Translation","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2312.16335","title":"LeanVec: Searching vectors faster by making them fit","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2401.17092","title":"NNOSE: Nearest Neighbor Occupational Skill Extraction","created":"2024-01-30","cited_by_count":5,"area":null},{"id":"2508.05970","title":"Impact-driven Context Filtering For Cross-file Code Completion","created":"2025-08-08","cited_by_count":5,"area":"rag"},{"id":"2212.00837","title":"Analogical Math Word Problems Solving with Enhanced Problem-Solution Association","created":"2022-12-01","cited_by_count":4,"area":"lr"},{"id":"2303.10942","title":"On-the-fly Text Retrieval for End-to-End ASR Adaptation","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2312.02429","title":"PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2409.18644","title":"Incorporating Precedents for Legal Judgement Prediction on European Court of Human Rights Cases","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2506.07309","title":"ConfRAG: Confidence-Guided Retrieval-Augmenting Generation","created":"2025-06-08","cited_by_count":4,"area":"rag"},{"id":"2302.13574","title":"kNN-BOX: A Unified Framework for Nearest Neighbor Generation","created":"2023-02-27","cited_by_count":3,"area":null},{"id":"2501.09092","title":"SteLLA: A Structured Grading System Using LLMs with RAG","created":"2025-01-15","cited_by_count":3,"area":null},{"id":"2204.02906","title":"Knowledge Base Index Compression via Dimensionality and Precision Reduction","created":"2022-04-06","cited_by_count":2,"area":null},{"id":"2210.15762","title":"Nearest Neighbor Language Models for Stylistic Controllable Generation","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2304.09649","title":"BRENT: Bidirectional Retrieval Enhanced Norwegian Transformer","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2310.08967","title":"Towards Example-Based NMT with Multi-Levenshtein Transformers","created":"2023-10-13","cited_by_count":2,"area":"rag"},{"id":"2406.06073","title":"Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2502.20245","title":"From Retrieval to Generation: Comparing Different Approaches","created":"2025-02-27","cited_by_count":2,"area":"rag"},{"id":"2301.12866","title":"N-Gram Nearest Neighbor Machine Translation","created":"2023-01-30","cited_by_count":1,"area":null},{"id":"2305.13034","title":"Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2307.06029","title":"Pluggable Neural Machine Translation Models via Memory-augmented Adapters","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2407.02138","title":"Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2410.03829","title":"Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2509.16729","title":"Angular Dispersion Accelerates $k$-Nearest Neighbors Machine Translation","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2510.17934","title":"AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM","created":"2025-10-20","cited_by_count":1,"area":"rag"},{"id":"2601.07903","title":"Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2601.14260","title":"End-to-End Transformer Acceleration Through Processing-in-Memory Architectures","created":"2025-11-21","cited_by_count":1,"area":"inference"},{"id":"2304.09058","title":"Revisiting k-NN for Fine-tuning Pre-trained Language Models","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2305.16599","title":"Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2409.20181","title":"Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2410.22347","title":"GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reduction","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2512.20145","title":"Retrieval-augmented Prompt Learning for Pre-trained Foundation Models","created":"2025-12-23","cited_by_count":0,"area":"rag"},{"id":"2604.19899","title":"A Reproducibility Study of Metacognitive Retrieval-Augmented Generation","created":"2026-04-21","cited_by_count":0,"area":"rag"},{"id":"2606.15416","title":"Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.29090","title":"AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering","created":"2026-06-27","cited_by_count":0,"area":"rag"},{"id":"2608.03839","title":"Oilbird: Training-Free Speculative Decoding with Keys the Verifier Already Computes","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2608.23851","title":"Does Episodic Memory Help Close the Lexical Frequency Gap in Sensitivity to Syntactic Contrasts? A Test Using Retrieval-Augmented Language Models","created":"2026-08-24","cited_by_count":0,"area":"rag"}],"next_cursor":null}