{"total":215,"rows":[{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839,"area":"rag"},{"id":"2405.14831","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","created":"2024-05-23","cited_by_count":281,"area":"rag"},{"id":"2502.14802","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","created":"2025-02-20","cited_by_count":231,"area":"rag"},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2406.05870","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","created":"2024-06-09","cited_by_count":102,"area":"rag"},{"id":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101,"area":"rag"},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77,"area":"rag"},{"id":"2403.03187","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","created":"2024-03-05","cited_by_count":73,"area":"rag"},{"id":"2403.10059","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","created":"2024-03-15","cited_by_count":55,"area":"rag"},{"id":"2410.02642","title":"Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers","created":"2024-10-03","cited_by_count":43,"area":"rag"},{"id":"2406.12430","title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers","created":"2024-06-18","cited_by_count":42,"area":"rag"},{"id":"2505.14146","title":"s3: You Don't Need That Much Data to Train a Search Agent via RL","created":"2025-05-20","cited_by_count":42,"area":"rag"},{"id":"2411.00300","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","created":"2024-11-01","cited_by_count":41,"area":"rag"},{"id":"2406.19215","title":"SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation","created":"2024-06-27","cited_by_count":40,"area":"rag"},{"id":"2407.01178","title":"$\\text{Memory}^3$: Language Modeling with Explicit Memory","created":"2024-07-01","cited_by_count":40,"area":"rag"},{"id":"2408.01262","title":"RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework","created":"2024-08-02","cited_by_count":39,"area":"rag"},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"id":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"area":"rag"},{"id":"2406.16828","title":"Ragnar\\\"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","created":"2024-06-24","cited_by_count":32,"area":"rag"},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31,"area":"rag"},{"id":"2402.11129","title":"BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering","created":"2024-02-16","cited_by_count":29,"area":"rag"},{"id":"2402.17497","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","created":"2024-02-27","cited_by_count":28,"area":"rag"},{"id":"2506.08938","title":"FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation","created":"2025-06-10","cited_by_count":28,"area":"rag"},{"id":"2501.18365","title":"RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects","created":"2025-01-30","cited_by_count":27,"area":"rag"},{"id":"2310.09949","title":"Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models","created":"2023-10-15","cited_by_count":23,"area":"rag"},{"id":"2410.15737","title":"Who's Who: Large Language Models Meet Knowledge Conflicts in Practice","created":"2024-10-21","cited_by_count":21,"area":"rag"},{"id":"2405.18111","title":"ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator","created":"2024-05-28","cited_by_count":19,"area":"rag"},{"id":"2502.20640","title":"LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation","created":"2025-02-28","cited_by_count":19,"area":"rag"},{"id":"2503.14649","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","created":"2025-03-18","cited_by_count":19,"area":"rag"},{"id":"2412.10543","title":"METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation","created":"2024-12-13","cited_by_count":17,"area":"rag"},{"id":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2506.15655","title":"cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree","created":"2025-06-18","cited_by_count":17,"area":"rag"},{"id":"2405.07530","title":"Prompt-based Code Completion via Multi-Retrieval Augmented Generation","created":"2024-05-13","cited_by_count":16,"area":"rag"},{"id":"2406.11357","title":"Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities","created":"2024-06-17","cited_by_count":16,"area":"rag"},{"id":"2505.10413","title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","created":"2025-05-15","cited_by_count":16,"area":"rag"},{"id":"2505.17762","title":"Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs","created":"2025-05-23","cited_by_count":16,"area":"rag"},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2603.15164","title":"HindSight: Evaluating LLM-Generated Research Ideas via Future Impact","created":"2026-03-16","cited_by_count":16,"area":"rag"},{"id":"2404.06910","title":"Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation","created":"2024-04-10","cited_by_count":15,"area":"rag"},{"id":"2412.11854","title":"Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference","created":"2024-12-16","cited_by_count":15,"area":"rag"},{"id":"2410.13716","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","created":"2024-10-17","cited_by_count":14,"area":"rag"},{"id":"2402.16457","title":"RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering","created":"2024-02-26","cited_by_count":13,"area":"rag"},{"id":"2501.02460","title":"Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications","created":"2025-01-05","cited_by_count":13,"area":"rag"},{"id":"2602.02579","title":"ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation","created":"2026-01-31","cited_by_count":13,"area":"rag"},{"id":"2406.09827","title":"A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention","created":"2024-06-14","cited_by_count":12,"area":"rag"},{"id":"2504.08231","title":"Out of Style: RAG's Fragility to Linguistic Variation","created":"2025-04-11","cited_by_count":11,"area":"rag"},{"id":"2504.17137","title":"MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation","created":"2025-04-23","cited_by_count":11,"area":"rag"},{"id":"2507.06956","title":"Investigating the Robustness of Retrieval-Augmented Generation at the Query Level","created":"2025-07-09","cited_by_count":11,"area":"rag"},{"id":"2512.16822","title":"MEPIC: Memory Efficient Position Independent Caching for LLM Serving","created":"2025-12-18","cited_by_count":11,"area":"rag"},{"id":"2411.16365","title":"Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines","created":"2024-11-25","cited_by_count":9,"area":"rag"},{"id":"2502.06205","title":"C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation","created":"2025-02-10","cited_by_count":9,"area":"rag"},{"id":"2502.10993","title":"RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization","created":"2025-02-16","cited_by_count":9,"area":"rag"},{"id":"2502.20969","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","created":"2025-02-28","cited_by_count":9,"area":"rag"},{"id":"2506.20051","title":"Controlled Retrieval-augmented Context Evaluation for Long-form RAG","created":"2025-06-24","cited_by_count":9,"area":"rag"},{"id":"2604.02985","title":"Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference","created":"2026-04-03","cited_by_count":9,"area":"rag"},{"id":"2407.00072","title":"Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback","created":"2024-06-21","cited_by_count":8,"area":"rag"},{"id":"2410.08821","title":"DeepNote: Note-Centric Deep Retrieval-Augmented Generation","created":"2024-10-11","cited_by_count":8,"area":"rag"},{"id":"2410.11446","title":"AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task","created":"2024-10-15","cited_by_count":8,"area":"rag"},{"id":"2410.15107","title":"Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models","created":"2024-10-19","cited_by_count":8,"area":"rag"},{"id":"2410.23090","title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","created":"2024-10-30","cited_by_count":8,"area":"rag"},{"id":"2502.18108","title":"Uncertainty Quantification in Retrieval Augmented Question Answering","created":"2025-02-25","cited_by_count":8,"area":"rag"},{"id":"2505.23052","title":"RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models","created":"2025-05-29","cited_by_count":8,"area":"rag"},{"id":"2506.00789","title":"RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems","created":"2025-06-01","cited_by_count":8,"area":"rag"},{"id":"2403.00982","title":"LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems","created":"2024-03-01","cited_by_count":7,"area":"rag"},{"id":"2502.11735","title":"MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables","created":"2025-02-17","cited_by_count":7,"area":"rag"},{"id":"2506.15862","title":"MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers","created":"2025-06-18","cited_by_count":7,"area":"rag"},{"id":"2510.18204","title":"RESCUE: Retrieval Augmented Secure Code Generation","created":"2025-10-21","cited_by_count":7,"area":"rag"},{"id":"2607.01299","title":"HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent Caching","created":"2026-07-01","cited_by_count":7,"area":"rag"},{"id":"2408.04414","title":"Enhancing Robustness of Retrieval-Augmented Language Models with In-Context Learning","created":"2024-08-08","cited_by_count":6,"area":"rag"},{"id":"2501.07813","title":"Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering","created":"2025-01-14","cited_by_count":6,"area":"rag"},{"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":"2505.05057","title":"Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware","created":"2025-05-08","cited_by_count":6,"area":"rag"},{"id":"2601.11004","title":"NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems","created":"2026-01-16","cited_by_count":6,"area":"rag"},{"id":"2411.01751","title":"RAGViz: Diagnose and Visualize Retrieval-Augmented Generation","created":"2024-11-04","cited_by_count":5,"area":"rag"},{"id":"2505.11271","title":"Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models","created":"2025-05-16","cited_by_count":5,"area":"rag"},{"id":"2505.15179","title":"RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry","created":"2025-05-21","cited_by_count":5,"area":"rag"},{"id":"2507.05713","title":"DRAGOn: Designing RAG On Periodically Updated Corpus","created":"2025-07-08","cited_by_count":5,"area":"rag"},{"id":"2508.05970","title":"Impact-driven Context Filtering For Cross-file Code Completion","created":"2025-08-08","cited_by_count":5,"area":"rag"},{"id":"2510.15312","title":"Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution","created":"2025-10-17","cited_by_count":5,"area":"rag"},{"id":"2601.12078","title":"Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization","created":"2026-01-17","cited_by_count":5,"area":"rag"},{"id":"2601.12904","title":"From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation","created":"2026-01-19","cited_by_count":5,"area":"rag"},{"id":"2603.24579","title":"MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination","created":"2026-03-25","cited_by_count":5,"area":"rag"},{"id":"2604.00865","title":"Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented Generation","created":"2026-04-01","cited_by_count":5,"area":"rag"},{"id":"2406.01876","title":"GRAM: Generative Retrieval Augmented Matching of Data Schemas in the Context of Data Security","created":"2024-06-04","cited_by_count":4,"area":"rag"},{"id":"2406.08116","title":"Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling","created":"2024-06-12","cited_by_count":4,"area":"rag"},{"id":"2409.20075","title":"BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain","created":"2024-09-30","cited_by_count":4,"area":"rag"},{"id":"2503.08398","title":"OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning","created":"2025-03-11","cited_by_count":4,"area":"rag"},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2504.07415","title":"RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction","created":"2025-04-10","cited_by_count":4,"area":"rag"},{"id":"2505.13258","title":"Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning","created":"2025-05-19","cited_by_count":4,"area":"rag"},{"id":"2508.01696","title":"CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy","created":"2025-08-03","cited_by_count":4,"area":"rag"},{"id":"2603.03919","title":"When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG","created":"2026-03-04","cited_by_count":4,"area":"rag"},{"id":"2603.23049","title":"PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving","created":"2026-03-24","cited_by_count":4,"area":"rag"},{"id":"2607.17715","title":"C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference","created":"2026-07-20","cited_by_count":4,"area":"rag"},{"id":"2411.14790","title":"KBAlign: Efficient Self Adaptation on Specific Knowledge Bases","created":"2024-11-22","cited_by_count":3,"area":"rag"},{"id":"2501.11929","title":"ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation","created":"2025-01-21","cited_by_count":3,"area":"rag"},{"id":"2502.13622","title":"REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models","created":"2025-02-19","cited_by_count":3,"area":"rag"},{"id":"2504.02411","title":"Adapting Large Language Models for Multi-Domain Retrieval-Augmented-Generation","created":"2025-04-03","cited_by_count":3,"area":"rag"},{"id":"2504.08930","title":"VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG","created":"2025-04-11","cited_by_count":3,"area":"rag"}],"next_cursor":"100"}