{"total":51,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2401.15391","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","created":"2024-01-27","cited_by_count":257,"area":"rag"},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2405.07437","title":"Evaluation of Retrieval-Augmented Generation: A Survey","created":"2024-05-13","cited_by_count":146,"area":"rag"},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83,"area":"rag"},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77,"area":"rag"},{"id":"2408.08067","title":"RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation","created":"2024-08-15","cited_by_count":61,"area":"rag"},{"id":"2502.11371","title":"RAG vs. GraphRAG: A Systematic Evaluation and Key Insights","created":"2025-02-17","cited_by_count":53,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2501.18636","title":"SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model","created":"2025-01-28","cited_by_count":32,"area":"rag"},{"id":"2412.13018","title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","created":"2024-12-17","cited_by_count":29,"area":"rag"},{"id":"2410.22832","title":"HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models","created":"2024-10-30","cited_by_count":27,"area":"rag"},{"id":"2404.12452","title":"Characterizing LLM Abstention Behavior in Science QA with Context Perturbations","created":"2024-04-18","cited_by_count":26,"area":null},{"id":"2602.18998","title":"Benchmark Test-Time Scaling of General LLM Agents","created":"2026-02-22","cited_by_count":26,"area":"lr"},{"id":"2404.02103","title":"CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems","created":"2024-04-02","cited_by_count":25,"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":"2504.14891","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","created":"2025-04-21","cited_by_count":20,"area":"rag"},{"id":"2506.07671","title":"GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation","created":"2025-06-09","cited_by_count":18,"area":null},{"id":"2410.12248","title":"CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity","created":"2024-10-16","cited_by_count":11,"area":"rag"},{"id":"2504.04062","title":"QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors","created":"2025-04-05","cited_by_count":11,"area":"rag"},{"id":"2504.17137","title":"MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation","created":"2025-04-23","cited_by_count":11,"area":"rag"},{"id":"2503.05587","title":"Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","created":"2025-03-07","cited_by_count":10,"area":"rag"},{"id":"2405.19010","title":"Evaluating the External and Parametric Knowledge Fusion of Large Language Models","created":"2024-05-29","cited_by_count":9,"area":null},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2408.10615","title":"Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2411.19710","title":"Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems","created":"2024-11-29","cited_by_count":8,"area":"rag"},{"id":"2502.04352","title":"Investigating the Robustness of Deductive Reasoning with Large Language Models","created":"2025-02-04","cited_by_count":8,"area":"lr"},{"id":"2509.18868","title":"Memory in Large Language Models: Mechanisms, Evaluation and Evolution","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2410.21970","title":"Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation","created":"2024-10-29","cited_by_count":6,"area":"rag"},{"id":"2408.05524","title":"Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs","created":"2024-08-10","cited_by_count":5,"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":"2411.10163","title":"Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2507.05424","title":"\"Lost-in-the-Later\": Framework for Quantifying Contextual Grounding in Large Language Models","created":"2025-07-07","cited_by_count":5,"area":"lr"},{"id":"2409.03759","title":"VERA: Validation and Evaluation of Retrieval-Augmented Systems","created":"2024-08-16","cited_by_count":4,"area":"rag"},{"id":"2501.08208","title":"ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems","created":"2025-01-14","cited_by_count":4,"area":"rag"},{"id":"2404.17347","title":"InspectorRAGet: An Introspection Platform for RAG Evaluation","created":"2024-04-26","cited_by_count":3,"area":"rag"},{"id":"2504.15689","title":"The Viability of Crowdsourcing for RAG Evaluation","created":"2025-04-22","cited_by_count":2,"area":"rag"},{"id":"2508.11758","title":"Can we Evaluate RAGs with Synthetic Data?","created":"2025-08-15","cited_by_count":2,"area":"synth"},{"id":"2404.12879","title":"Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation","created":"2024-04-19","cited_by_count":1,"area":"rag"},{"id":"2506.03901","title":"Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems","created":"2025-06-04","cited_by_count":1,"area":"rag"},{"id":"2511.04502","title":"RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG","created":"2025-11-06","cited_by_count":1,"area":"rag"},{"id":"2604.02640","title":"Overcoming the \"Impracticality\" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework","created":"2026-04-03","cited_by_count":1,"area":"rag"},{"id":"2610.11183","title":"RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation","created":"2026-10-08","cited_by_count":1,"area":"rag"},{"id":"2510.27400","title":"Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2601.05260","title":"Quantifying Document Impact in RAG-LLMs","created":"2025-10-27","cited_by_count":0,"area":"rag"},{"id":"2601.11585","title":"Entropic Context Shaping: Information-Theoretic Filtering for Context-Aware LLM Agents","created":"2026-01-01","cited_by_count":0,"area":"agents"},{"id":"2605.09661","title":"MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies","created":"2026-05-10","cited_by_count":0,"area":"rag"},{"id":"2605.26476","title":"FAB-Bench: A Framework for Adaptive RAG Benchmarking in Semiconductor Manufacturing","created":"2026-05-26","cited_by_count":0,"area":"rag"},{"id":"2608.20097","title":"TrustRAG: Blockchain-Enhanced RAG via Committee-Based Credibility Scoring","created":"2026-08-20","cited_by_count":0,"area":"rag"},{"id":"2609.38543","title":"MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}