{"total":30,"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":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64,"area":"rag"},{"id":"2405.03279","title":"Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning","created":"2024-05-06","cited_by_count":40,"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":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"area":"rag"},{"id":"2404.02319","title":"Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization","created":"2024-04-02","cited_by_count":30,"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":"2503.10720","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","created":"2025-03-13","cited_by_count":19,"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":"2405.03085","title":"Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation","created":"2024-05-06","cited_by_count":16,"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":"2507.22931","title":"Enhancing RAG Efficiency with Adaptive Context Compression","created":"2025-07-24","cited_by_count":8,"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":"2403.15268","title":"Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering","created":"2024-03-22","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":"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":"2508.15253","title":"Conflict-Aware Soft Prompting for Retrieval-Augmented Generation","created":"2025-08-21","cited_by_count":5,"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":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2502.14925","title":"CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs","created":"2025-02-19","cited_by_count":2,"area":"rag"},{"id":"2603.09222","title":"EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering","created":"2026-03-10","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":"2608.13588","title":"IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering","created":"2026-07-12","cited_by_count":1,"area":"rag"},{"id":"2604.14403","title":"A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation","created":"2026-04-15","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":"2608.19535","title":"From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG","created":"2026-08-20","cited_by_count":0,"area":"rag"},{"id":"2609.05152","title":"Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.14245","title":"The Attribution-Compression Frontier in Retrieval-Augmented Generation","created":"2026-09-13","cited_by_count":0,"area":"rag"},{"id":"2609.22100","title":"AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation","created":"2026-08-12","cited_by_count":0,"area":"rag"}],"next_cursor":null}