{"total":146,"rows":[{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"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":"2405.07437","title":"Evaluation of Retrieval-Augmented Generation: A Survey","created":"2024-05-13","cited_by_count":146,"area":"rag"},{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117,"area":"rag"},{"id":"2404.10198","title":"ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence","created":"2024-04-16","cited_by_count":113,"area":"rag"},{"id":"2404.13781","title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","created":"2024-04-21","cited_by_count":90,"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":"2407.13193","title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","created":"2024-07-18","cited_by_count":71,"area":"rag"},{"id":"2407.08488","title":"Lynx: An Open Source Hallucination Evaluation Model","created":"2024-07-11","cited_by_count":57,"area":"rag"},{"id":"2401.17043","title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models","created":"2024-01-30","cited_by_count":50,"area":"rag"},{"id":"2411.00300","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","created":"2024-11-01","cited_by_count":41,"area":"rag"},{"id":"2408.01262","title":"RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework","created":"2024-08-02","cited_by_count":39,"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":"2502.17125","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","created":"2025-02-24","cited_by_count":34,"area":"rag"},{"id":"2410.23000","title":"Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall","created":"2024-10-30","cited_by_count":32,"area":"rag"},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31,"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":"2502.09977","title":"LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing","created":"2025-02-14","cited_by_count":29,"area":"rag"},{"id":"2506.00054","title":"Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers","created":"2025-05-28","cited_by_count":27,"area":"rag"},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26,"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":"2405.13622","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation","created":"2024-05-22","cited_by_count":25,"area":"rag"},{"id":"2503.01478","title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction","created":"2025-03-03","cited_by_count":24,"area":"rag"},{"id":"2504.15068","title":"The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models","created":"2025-04-21","cited_by_count":24,"area":"rag"},{"id":"2412.13746","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","created":"2024-12-18","cited_by_count":23,"area":"rag"},{"id":"2409.09046","title":"HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications","created":"2024-08-29","cited_by_count":22,"area":"rag"},{"id":"2407.12873","title":"Evaluation of RAG Metrics for Question Answering in the Telecom Domain","created":"2024-07-15","cited_by_count":20,"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":"2505.17471","title":"FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain","created":"2025-05-23","cited_by_count":16,"area":"rag"},{"id":"2409.11598","title":"Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation","created":"2024-09-17","cited_by_count":15,"area":"rag"},{"id":"2504.15205","title":"Support Evaluation for the TREC 2024 RAG Track: Comparing Human versus LLM Judges","created":"2025-04-21","cited_by_count":14,"area":"rag"},{"id":"2509.26184","title":"Auto-ARGUE: LLM-Based Report Generation Evaluation","created":"2025-09-30","cited_by_count":14,"area":"rag"},{"id":"2402.16457","title":"RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering","created":"2024-02-26","cited_by_count":13,"area":"rag"},{"id":"2412.21023","title":"EdgeRAG: Online-Indexed RAG for Edge Devices","created":"2024-12-30","cited_by_count":13,"area":"rag"},{"id":"2406.09818","title":"ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures","created":"2024-06-14","cited_by_count":12,"area":"rag"},{"id":"2504.08694","title":"TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning","created":"2025-04-11","cited_by_count":12,"area":"rag"},{"id":"2406.14783","title":"Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework","created":"2024-06-20","cited_by_count":11,"area":"rag"},{"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":"2407.05925","title":"Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loop","created":"2024-07-08","cited_by_count":10,"area":"rag"},{"id":"2506.20051","title":"Controlled Retrieval-augmented Context Evaluation for Long-form RAG","created":"2025-06-24","cited_by_count":9,"area":"rag"},{"id":"2410.15531","title":"Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage","created":"2024-10-20","cited_by_count":8,"area":"rag"},{"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":"2502.18817","title":"Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models","created":"2025-02-26","cited_by_count":8,"area":"rag"},{"id":"2503.09902","title":"Conversational Gold: Evaluating Personalized Conversational Search System using Gold Nuggets","created":"2025-03-12","cited_by_count":8,"area":"rag"},{"id":"2506.20978","title":"Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality","created":"2025-06-26","cited_by_count":8,"area":"rag"},{"id":"2605.03534","title":"SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation","created":"2026-05-05","cited_by_count":8,"area":"rag"},{"id":"2406.18064","title":"Evaluating Quality of Answers for Retrieval-Augmented Generation: A Strong LLM Is All You Need","created":"2024-06-26","cited_by_count":7,"area":"rag"},{"id":"2410.12812","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","created":"2024-10-01","cited_by_count":7,"area":"rag"},{"id":"2502.17163","title":"MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation","created":"2025-02-24","cited_by_count":7,"area":"rag"},{"id":"2504.20119","title":"Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets","created":"2025-04-28","cited_by_count":7,"area":"rag"},{"id":"2509.13930","title":"Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG","created":"2025-09-17","cited_by_count":7,"area":"rag"},{"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":"2510.08109","title":"VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents","created":"2025-10-09","cited_by_count":6,"area":"rag"},{"id":"2601.05866","title":"FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG","created":"2026-01-09","cited_by_count":6,"area":"rag"},{"id":"2601.18777","title":"PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking Estimation","created":"2026-01-26","cited_by_count":6,"area":"rag"},{"id":"2602.00296","title":"RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing","created":"2026-01-30","cited_by_count":6,"area":"rag"},{"id":"2408.02545","title":"RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation","created":"2024-08-05","cited_by_count":5,"area":"rag"},{"id":"2412.05206","title":"ConQRet: Benchmarking Fine-Grained Evaluation of Retrieval Augmented Argumentation with LLM Judges","created":"2024-12-06","cited_by_count":5,"area":"rag"},{"id":"2412.12300","title":"Unanswerability Evaluation for Retrieval Augmented Generation","created":"2024-12-16","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":"2505.13258","title":"Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning","created":"2025-05-19","cited_by_count":4,"area":"rag"},{"id":"2505.13538","title":"RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines","created":"2025-05-18","cited_by_count":4,"area":"rag"},{"id":"2508.06056","title":"RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation","created":"2025-08-08","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":"2406.14162","title":"DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation","created":"2024-06-20","cited_by_count":3,"area":"rag"},{"id":"2505.08728","title":"Securing RAG: A Risk Assessment and Mitigation Framework","created":"2025-05-13","cited_by_count":3,"area":"rag"},{"id":"2506.20128","title":"CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation","created":"2025-06-25","cited_by_count":3,"area":"rag"},{"id":"2508.15437","title":"Test-time Corpus Feedback: From Retrieval to RAG","created":"2025-08-21","cited_by_count":3,"area":"rag"},{"id":"2512.05411","title":"A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems","created":"2025-12-05","cited_by_count":3,"area":"rag"},{"id":"2410.03461","title":"Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation","created":"2024-10-04","cited_by_count":2,"area":"rag"},{"id":"2410.14567","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","created":"2024-10-18","cited_by_count":2,"area":"rag"},{"id":"2411.00294","title":"LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Models","created":"2024-11-01","cited_by_count":2,"area":"rag"},{"id":"2504.07803","title":"A System for Comprehensive Assessment of RAG Frameworks","created":"2025-04-10","cited_by_count":2,"area":"rag"},{"id":"2504.15689","title":"The Viability of Crowdsourcing for RAG Evaluation","created":"2025-04-22","cited_by_count":2,"area":"rag"},{"id":"2505.08445","title":"Optimizing Retrieval-Augmented Generation: Analysis of Hyperparameter Impact on Performance and Efficiency","created":"2025-05-13","cited_by_count":2,"area":"rag"},{"id":"2505.23299","title":"Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs","created":"2025-05-29","cited_by_count":2,"area":"rag"},{"id":"2507.03608","title":"Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)","created":"2025-07-04","cited_by_count":2,"area":"rag"},{"id":"2507.22927","title":"PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation","created":"2025-07-23","cited_by_count":2,"area":"rag"},{"id":"2508.20083","title":"DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)","created":"2025-08-27","cited_by_count":2,"area":"rag"},{"id":"2511.04696","title":"EncouRAGe: Evaluating RAG Local, Fast, and Reliable","created":"2025-10-31","cited_by_count":2,"area":"rag"},{"id":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2603.03541","title":"RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering","created":"2026-03-03","cited_by_count":2,"area":"rag"},{"id":"2603.11772","title":"Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documents","created":"2026-03-12","cited_by_count":2,"area":"rag"},{"id":"2604.01733","title":"From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents","created":"2026-04-02","cited_by_count":2,"area":"rag"},{"id":"2606.06748","title":"Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection","created":"2026-06-04","cited_by_count":2,"area":"rag"},{"id":"2607.18155","title":"Testing Retrieval-Augmented Generation Systems with Chunk Coverage","created":"2026-07-20","cited_by_count":2,"area":"rag"},{"id":"2607.26843","title":"When Knowledge Changes: Metamorphic Testing of RAG Systems with Mutations","created":"2026-07-29","cited_by_count":2,"area":"rag"},{"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":"2408.15171","title":"Measuring text summarization factuality using atomic facts entailment metrics in the context of retrieval augmented generation","created":"2024-08-27","cited_by_count":1,"area":"rag"},{"id":"2412.17558","title":"A Survey of Query Optimization in Large Language Models","created":"2024-12-23","cited_by_count":1,"area":"rag"},{"id":"2502.19209","title":"Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation","created":"2025-02-26","cited_by_count":1,"area":"rag"},{"id":"2502.19596","title":"Reference-Aligned Retrieval-Augmented Question Answering over Heterogeneous Proprietary Documents","created":"2025-02-26","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":"2601.05265","title":"Cross-Document Topic-Aligned Chunking for Retrieval-Augmented Generation","created":"2025-11-08","cited_by_count":1,"area":"rag"},{"id":"2605.27494","title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","created":"2026-05-26","cited_by_count":1,"area":"rag"},{"id":"2606.29645","title":"Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichment","created":"2026-06-28","cited_by_count":1,"area":"rag"},{"id":"2607.00725","title":"Recall Is Not Enough: A Reader-Context Diagnostic for Budget-Constrained Retrieval-Augmented Generation","created":"2026-07-01","cited_by_count":1,"area":"rag"},{"id":"2607.01852","title":"Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts","created":"2026-07-02","cited_by_count":1,"area":"rag"}],"next_cursor":"100"}