{"total":50,"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":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532,"area":"rag"},{"id":"2409.05591","title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","created":"2024-09-09","cited_by_count":119,"area":"rag"},{"id":"2406.15319","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","created":"2024-06-21","cited_by_count":108,"area":"rag"},{"id":"2404.08189","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","created":"2024-04-12","cited_by_count":93,"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":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65,"area":"rag"},{"id":"2504.09795","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","created":"2025-04-14","cited_by_count":59,"area":"rag"},{"id":"2409.01666","title":"In Defense of RAG in the Era of Long-Context Language Models","created":"2024-09-03","cited_by_count":53,"area":"rag"},{"id":"2410.18050","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","created":"2024-10-23","cited_by_count":49,"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":"2409.15355","title":"Block-Attention for Efficient Prefilling","created":"2024-09-14","cited_by_count":37,"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":"2212.08153","title":"FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference","created":"2022-12-15","cited_by_count":31,"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":"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":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","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":"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":"2410.09584","title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","created":"2024-10-12","cited_by_count":9,"area":"rag"},{"id":"2401.07793","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","created":"2024-01-15","cited_by_count":7,"area":"rag"},{"id":"2409.13385","title":"Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2024-09-20","cited_by_count":5,"area":"rag"},{"id":"2504.01281","title":"Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding","created":"2025-04-02","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":"2508.15253","title":"Conflict-Aware Soft Prompting for Retrieval-Augmented Generation","created":"2025-08-21","cited_by_count":5,"area":"rag"},{"id":"2511.09803","title":"Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG","created":"2025-11-12","cited_by_count":5,"area":"rag"},{"id":"2511.20227","title":"HKRAG: Holistic Knowledge Retrieval-Augmented Generation Over Visually-Rich Documents","created":"2025-11-25","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":"2405.15198","title":"RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference","created":"2024-05-24","cited_by_count":4,"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":"2505.17118","title":"After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation","created":"2025-05-21","cited_by_count":4,"area":"rag"},{"id":"2403.04180","title":"RATSF: Empowering Customer Service Volume Management through Retrieval-Augmented Time-Series Forecasting","created":"2024-03-07","cited_by_count":3,"area":"rag"},{"id":"2603.00846","title":"Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models","created":"2026-03-01","cited_by_count":3,"area":"rag"},{"id":"2606.05875","title":"QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving","created":"2026-06-04","cited_by_count":3,"area":"rag"},{"id":"2407.12057","title":"NinjaLLM: Fast, Scalable and Cost-effective RAG using Amazon SageMaker and AWS Trainium and Inferentia2","created":"2024-07-11","cited_by_count":2,"area":"rag"},{"id":"2503.02922","title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","created":"2025-03-04","cited_by_count":2,"area":"rag"},{"id":"2512.22195","title":"MatKV: Trading Compute for Flash Storage in LLM Inference","created":"2025-12-20","cited_by_count":2,"area":"rag"},{"id":"2606.04302","title":"LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding","created":"2026-06-03","cited_by_count":2,"area":"rag"},{"id":"2505.20320","title":"Less Context, Same Performance: A RAG Framework for Resource-Efficient LLM-Based Clinical NLP","created":"2025-05-23","cited_by_count":1,"area":"rag"},{"id":"2604.25080","title":"CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration","created":"2026-04-28","cited_by_count":1,"area":"rag"},{"id":"2605.25716","title":"An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG","created":"2026-05-25","cited_by_count":1,"area":"rag"},{"id":"2609.14762","title":"TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps","created":"2026-09-13","cited_by_count":1,"area":"rag"},{"id":"2510.20878","title":"HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2605.03799","title":"Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF","created":"2026-05-05","cited_by_count":0,"area":"rag"},{"id":"2605.25039","title":"AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy","created":"2026-05-24","cited_by_count":0,"area":"rag"},{"id":"2607.07740","title":"Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE","created":"2026-07-08","cited_by_count":0,"area":"rag"},{"id":"2607.24554","title":"DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding","created":"2026-07-27","cited_by_count":0,"area":"rag"},{"id":"2608.02560","title":"Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection","created":"2026-08-03","cited_by_count":0,"area":"rag"},{"id":"2609.10372","title":"PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving","created":"2026-09-09","cited_by_count":0,"area":"rag"},{"id":"2610.15186","title":"SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG","created":"2026-10-10","cited_by_count":0,"area":"rag"}],"next_cursor":null}