{"total":83,"rows":[{"id":"2407.16833","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","created":"2024-07-23","cited_by_count":119,"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":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87,"area":"rag"},{"id":"2310.07554","title":"A Multi-Task Embedder For Retrieval Augmented LLMs","created":"2023-10-11","cited_by_count":64,"area":"rag"},{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63,"area":"rag"},{"id":"2407.14482","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","created":"2024-07-19","cited_by_count":53,"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":"2412.10704","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":41,"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":"2402.09760","title":"Grounding Language Model with Chunking-Free In-Context Retrieval","created":"2024-02-15","cited_by_count":30,"area":"rag"},{"id":"2502.09977","title":"LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing","created":"2025-02-14","cited_by_count":29,"area":"rag"},{"id":"2402.12174","title":"BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence","created":"2024-02-19","cited_by_count":28,"area":"rag"},{"id":"2412.13746","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","created":"2024-12-18","cited_by_count":23,"area":"rag"},{"id":"2502.14245","title":"Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering","created":"2025-02-20","cited_by_count":22,"area":"rag"},{"id":"2503.00353","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","created":"2025-03-01","cited_by_count":20,"area":"rag"},{"id":"2503.09600","title":"MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System","created":"2025-03-12","cited_by_count":19,"area":"rag"},{"id":"2503.10720","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","created":"2025-03-13","cited_by_count":19,"area":"rag"},{"id":"2410.12788","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","created":"2024-10-16","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":"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":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2402.11573","title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","created":"2024-02-18","cited_by_count":15,"area":"rag"},{"id":"2606.24775","title":"Are We Ready For An Agent-Native Memory System?","created":"2026-06-23","cited_by_count":15,"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":"2509.11552","title":"HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking","created":"2025-09-15","cited_by_count":12,"area":"rag"},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"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":"2401.07793","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","created":"2024-01-15","cited_by_count":7,"area":"rag"},{"id":"2508.03793","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","created":"2025-08-05","cited_by_count":7,"area":"rag"},{"id":"2409.15699","title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation","created":"2024-09-24","cited_by_count":6,"area":"rag"},{"id":"2501.09940","title":"Passage Segmentation of Documents for Extractive Question Answering","created":"2025-01-17","cited_by_count":6,"area":"rag"},{"id":"2503.03434","title":"RASD: Retrieval-Augmented Speculative Decoding","created":"2025-03-05","cited_by_count":6,"area":"rag"},{"id":"2512.17220","title":"Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding","created":"2025-12-19","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":"2601.17212","title":"DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation","created":"2026-01-23","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":"2505.23277","title":"Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression","created":"2025-05-29","cited_by_count":4,"area":"rag"},{"id":"2506.05167","title":"ECoRAG: Evidentiality-guided Compression for Long Context RAG","created":"2025-06-05","cited_by_count":4,"area":"rag"},{"id":"2507.22533","title":"CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Records","created":"2025-07-30","cited_by_count":4,"area":"rag"},{"id":"2511.16326","title":"ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning","created":"2025-11-20","cited_by_count":4,"area":"rag"},{"id":"2601.09913","title":"Continuum Memory Architectures for Long-Horizon LLM Agents","created":"2026-01-14","cited_by_count":3,"area":"rag"},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2604.12610","title":"Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs","created":"2026-04-14","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":"2406.13249","title":"R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation","created":"2024-06-19","cited_by_count":2,"area":"rag"},{"id":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2503.02603","title":"OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing","created":"2025-03-04","cited_by_count":2,"area":"rag"},{"id":"2505.06569","title":"MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG","created":"2025-05-10","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":"2502.12502","title":"Efficient OpAmp Adaptation for Zoom Attention to Golden Contexts","created":"2025-02-18","cited_by_count":1,"area":"rag"},{"id":"2506.13778","title":"Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning","created":"2025-06-09","cited_by_count":1,"area":"rag"},{"id":"2508.09755","title":"Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation","created":"2025-08-13","cited_by_count":1,"area":"rag"},{"id":"2601.08670","title":"Parallel Context-of-Experts Decoding for Retrieval Augmented Generation","created":"2026-01-13","cited_by_count":1,"area":"rag"},{"id":"2601.18527","title":"Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models","created":"2026-01-26","cited_by_count":1,"area":"rag"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2606.09441","title":"SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance","created":"2026-06-08","cited_by_count":1,"area":"rag"},{"id":"2607.00725","title":"Recall Is Not Enough: A Reader-Context Diagnostic for Budget-Constrained Retrieval-Augmented Generation","created":"2026-07-01","cited_by_count":1,"area":"rag"},{"id":"2607.17108","title":"Evidence Interfaces Shape How Retrieval-Augmented Readers Use Support","created":"2026-07-19","cited_by_count":1,"area":"rag"},{"id":"2609.03874","title":"STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation","created":"2026-09-03","cited_by_count":1,"area":"rag"},{"id":"2410.04790","title":"PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA","created":"2024-10-07","cited_by_count":0,"area":"rag"},{"id":"2412.14905","title":"Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation","created":"2024-12-19","cited_by_count":0,"area":"rag"},{"id":"2505.17206","title":"FB-RAG: Improving RAG with Forward and Backward Lookup","created":"2025-05-22","cited_by_count":0,"area":"rag"},{"id":"2509.21865","title":"Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding","created":"2025-09-26","cited_by_count":0,"area":"rag"},{"id":"2602.12278","title":"AttentionRetriever: Attention Layers are Secretly Long Document Retrievers","created":"2026-02-12","cited_by_count":0,"area":"rag"},{"id":"2603.11650","title":"QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate","created":"2026-03-12","cited_by_count":0,"area":"rag"},{"id":"2603.26667","title":"M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation","created":"2026-01-06","cited_by_count":0,"area":"rag"},{"id":"2604.12766","title":"NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation","created":"2026-04-14","cited_by_count":0,"area":"rag"},{"id":"2604.28157","title":"FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption","created":"2026-04-30","cited_by_count":0,"area":"rag"},{"id":"2605.15913","title":"Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation","created":"2026-05-15","cited_by_count":0,"area":"rag"},{"id":"2605.27432","title":"FD-RAG: Federated Dual-System Retrieval-Augmented Generation","created":"2026-05-22","cited_by_count":0,"area":"rag"},{"id":"2605.30029","title":"RAISE: RAG Design as an Architecture Search Problem","created":"2026-05-28","cited_by_count":0,"area":"rag"},{"id":"2606.18508","title":"MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval","created":"2026-06-16","cited_by_count":0,"area":"rag"},{"id":"2607.21324","title":"GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG","created":"2026-07-23","cited_by_count":0,"area":"rag"},{"id":"2608.07458","title":"CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG","created":"2026-08-07","cited_by_count":0,"area":"rag"},{"id":"2608.23252","title":"The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2609.17564","title":"Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs","created":"2026-07-23","cited_by_count":0,"area":"rag"},{"id":"2609.33503","title":"RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse","created":"2026-09-27","cited_by_count":0,"area":"rag"},{"id":"2610.06902","title":"Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA","created":"2026-09-30","cited_by_count":0,"area":"rag"},{"id":"2610.12617","title":"GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports","created":"2026-10-08","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}