{"total":57,"rows":[{"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":"2402.17840","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","created":"2024-02-27","cited_by_count":76,"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":"2411.08249","title":"Retrieval Augmented Time Series Forecasting","created":"2024-11-12","cited_by_count":46,"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":"2310.10445","title":"MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities","created":"2023-10-16","cited_by_count":38,"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":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35,"area":"rag"},{"id":"2502.17125","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","created":"2025-02-24","cited_by_count":34,"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":"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":"2306.13421","title":"Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval","created":"2023-06-23","cited_by_count":20,"area":"rag"},{"id":"2406.17186","title":"CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation","created":"2024-06-24","cited_by_count":18,"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":"2606.02553","title":"LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation","created":"2026-06-01","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":"2505.15561","title":"Do RAG Systems Really Suffer From Positional Bias?","created":"2025-05-21","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":"2406.11830","title":"Language Modeling with Editable External Knowledge","created":"2024-06-17","cited_by_count":9,"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":"2410.03780","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","created":"2024-10-03","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":"2508.04724","title":"Understanding protein function with a multimodal retrieval-augmented foundation model","created":"2025-08-05","cited_by_count":6,"area":"rag"},{"id":"2506.02279","title":"ImpRAG: Retrieval-Augmented Generation with Implicit Queries","created":"2025-06-02","cited_by_count":5,"area":"rag"},{"id":"2601.02993","title":"Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation","created":"2026-01-06","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":"2603.20218","title":"An experimental study of KV cache reuse strategies in chunk-level caching systems","created":"2026-03-03","cited_by_count":5,"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":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2411.02617","title":"TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network","created":"2024-11-04","cited_by_count":2,"area":"rag"},{"id":"2605.11864","title":"Very Efficient Listwise Multimodal Reranking for Long Documents","created":"2026-05-12","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":"2606.13126","title":"MiniPIC: Flexible Position-Independent Caching in <100LOC","created":"2026-06-11","cited_by_count":2,"area":"rag"},{"id":"2408.05026","title":"Retrieval-augmented code completion for local projects using large language models","created":"2024-08-09","cited_by_count":1,"area":"rag"},{"id":"2409.19745","title":"PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead","created":"2024-09-29","cited_by_count":1,"area":"rag"},{"id":"2601.11553","title":"PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices","created":"2025-12-10","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":"2603.07612","title":"KohakuRAG: A simple RAG framework with hierarchical document indexing","created":"2026-03-08","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":"2606.16494","title":"Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering","created":"2026-06-15","cited_by_count":1,"area":"rag"},{"id":"2410.00004","title":"Retro-li: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization","created":"2024-09-12","cited_by_count":0,"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":"2410.18105","title":"Improving Embedding Accuracy for Document Retrieval Using Entity Relationship Maps and Model-Aware Contrastive Sampling","created":"2024-10-08","cited_by_count":0,"area":"rag"},{"id":"2502.02249","title":"Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation","created":"2025-02-04","cited_by_count":0,"area":"rag"},{"id":"2502.11101","title":"CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation","created":"2025-02-16","cited_by_count":0,"area":"rag"},{"id":"2603.23508","title":"Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems","created":"2026-03-04","cited_by_count":0,"area":"rag"},{"id":"2604.13938","title":"ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding","created":"2026-04-15","cited_by_count":0,"area":"rag"},{"id":"2605.12335","title":"EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records","created":"2026-05-12","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":"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":"2608.12121","title":"QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving","created":"2026-08-12","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":"2609.35139","title":"CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion","created":"2026-09-28","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}