{"total":42,"rows":[{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123,"area":"rag"},{"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":"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":"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":"2412.15605","title":"Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks","created":"2024-12-20","cited_by_count":38,"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":"2412.10543","title":"METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation","created":"2024-12-13","cited_by_count":17,"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":"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":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2407.19794","title":"Introducing a new hyper-parameter for RAG: Context Window Utilization","created":"2024-07-29","cited_by_count":8,"area":"rag"},{"id":"2511.17560","title":"$A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving","created":"2025-11-13","cited_by_count":8,"area":"rag"},{"id":"2511.17908","title":"Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction","created":"2025-11-22","cited_by_count":6,"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":"2511.07328","title":"Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training","created":"2025-11-10","cited_by_count":4,"area":"rag"},{"id":"2506.22518","title":"Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation","created":"2025-06-26","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":"2410.11195","title":"Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Models","created":"2024-10-15","cited_by_count":2,"area":"rag"},{"id":"2412.06078","title":"Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAG","created":"2024-12-08","cited_by_count":2,"area":"rag"},{"id":"2503.16071","title":"Tuning LLMs by RAG Principles: Towards LLM-native Memory","created":"2025-03-20","cited_by_count":2,"area":"rag"},{"id":"2512.23836","title":"Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?","created":"2025-12-29","cited_by_count":2,"area":"rag"},{"id":"2604.03240","title":"Scaling DPPs for RAG: Density Meets Diversity","created":"2026-02-04","cited_by_count":2,"area":"rag"},{"id":"2602.08070","title":"IRB: Automated Generation of Robust Factuality Benchmarks","created":"2026-02-08","cited_by_count":1,"area":"rag"},{"id":"2603.10765","title":"RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems","created":"2026-03-11","cited_by_count":1,"area":"rag"},{"id":"2604.14339","title":"Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation","created":"2026-04-15","cited_by_count":1,"area":"rag"},{"id":"2411.19478","title":"Zero-Indexing Internet Search Augmented Generation for Large Language Models","created":"2024-11-29","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":"2501.07523","title":"Parallel Key-Value Cache Fusion for Position Invariant RAG","created":"2025-01-13","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":"2605.27294","title":"Separating Semantic Competition from Context Length in RAG Reading","created":"2026-05-26","cited_by_count":0,"area":"rag"},{"id":"2605.29712","title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","created":"2026-05-28","cited_by_count":0,"area":"rag"},{"id":"2606.05901","title":"Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)","created":"2026-06-04","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":"2607.16209","title":"Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning","created":"2026-05-10","cited_by_count":0,"area":"rag"},{"id":"2607.21599","title":"Decoupled Attention Fusion: Accelerating RAG with Efficient KV Cache Reuse","created":"2026-05-03","cited_by_count":0,"area":"rag"},{"id":"2608.03297","title":"Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks","created":"2026-08-04","cited_by_count":0,"area":"rag"},{"id":"2608.15547","title":"BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language","created":"2026-08-16","cited_by_count":0,"area":"rag"},{"id":"2609.07093","title":"Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering","created":"2026-09-07","cited_by_count":0,"area":"rag"},{"id":"2609.09768","title":"Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?","created":"2026-09-09","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":"2610.15186","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}