{"total":19,"rows":[{"id":"2403.05676","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","created":"2024-03-08","cited_by_count":28,"area":"rag"},{"id":"2310.09949","title":"Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models","created":"2023-10-15","cited_by_count":23,"area":"rag"},{"id":"2405.04700","title":"Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures","created":"2024-05-07","cited_by_count":12,"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":"2310.01329","title":"BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models","created":"2023-10-02","cited_by_count":5,"area":"rag"},{"id":"2504.05220","title":"Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation","created":"2025-04-07","cited_by_count":5,"area":"rag"},{"id":"2405.15984","title":"Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning","created":"2024-05-24","cited_by_count":4,"area":"rag"},{"id":"2406.01876","title":"GRAM: Generative Retrieval Augmented Matching of Data Schemas in the Context of Data Security","created":"2024-06-04","cited_by_count":4,"area":"rag"},{"id":"2501.10534","title":"4bit-Quantization in Vector-Embedding for RAG","created":"2025-01-17","cited_by_count":4,"area":"rag"},{"id":"2406.10251","title":"The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs","created":"2024-06-10","cited_by_count":3,"area":"rag"},{"id":"2406.12069","title":"Satyrn: A Platform for Analytics Augmented Generation","created":"2024-06-17","cited_by_count":2,"area":"rag"},{"id":"2504.15302","title":"RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU","created":"2025-04-17","cited_by_count":2,"area":"rag"},{"id":"2510.15620","title":"On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding","created":"2025-10-17","cited_by_count":1,"area":"rag"},{"id":"2607.01831","title":"Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference","created":"2026-07-02","cited_by_count":1,"area":"rag"},{"id":"2607.03615","title":"The Powerless Noise: How Experimental Settings Shape the Reported Power of Noise","created":"2026-07-03","cited_by_count":1,"area":"rag"},{"id":"2605.03799","title":"Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF","created":"2026-05-05","cited_by_count":0,"area":"rag"},{"id":"2605.26019","title":"Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Service","created":"2026-05-25","cited_by_count":0,"area":"rag"},{"id":"2609.02760","title":"Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents","created":"2026-09-02","cited_by_count":0,"area":"rag"},{"id":"2609.15242","title":"Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain","created":"2026-09-14","cited_by_count":0,"area":"rag"}],"next_cursor":null}