{"total":17,"rows":[{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256,"area":"rag"},{"id":"2305.02437","title":"Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory","created":"2023-05-03","cited_by_count":103,"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":"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":"2306.13421","title":"Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval","created":"2023-06-23","cited_by_count":20,"area":"rag"},{"id":"2406.07348","title":"DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering","created":"2024-06-11","cited_by_count":14,"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":"2401.07793","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","created":"2024-01-15","cited_by_count":7,"area":"rag"},{"id":"2605.05806","title":"Retrieval from Within: An Intrinsic Capability of Attention-Based Models","created":"2026-05-07","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":"2604.14339","title":"Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation","created":"2026-04-15","cited_by_count":1,"area":"rag"},{"id":"2509.08596","title":"LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge","created":"2025-09-10","cited_by_count":0,"area":"rag"},{"id":"2603.06593","title":"Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation","created":"2026-02-04","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":"2606.11700","title":"CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring","created":"2026-06-10","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":"2610.08463","title":"UNREAL: Unifying Retrieval and Long-Context with a Single Model","created":"2026-10-06","cited_by_count":0,"area":"rag"}],"next_cursor":null}