{"total":265,"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":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"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":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"area":null},{"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":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"area":null},{"id":"2403.07008","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","created":"2024-03-09","cited_by_count":57,"area":"synth"},{"id":"2407.08488","title":"Lynx: An Open Source Hallucination Evaluation Model","created":"2024-07-11","cited_by_count":57,"area":"rag"},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"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":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49,"area":null},{"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":"2606.04990","title":"From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents","created":"2026-06-03","cited_by_count":37,"area":"agents"},{"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":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"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":"2402.17826","title":"Prediction-Powered Ranking of Large Language Models","created":"2024-02-27","cited_by_count":29,"area":null},{"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":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"area":null},{"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":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"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":"2506.18203","title":"Shrinking the Generation-Verification Gap with Weak Verifiers","created":"2025-06-22","cited_by_count":24,"area":null},{"id":"2405.00982","title":"On the Evaluation of Machine-Generated Reports","created":"2024-05-02","cited_by_count":23,"area":null},{"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":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"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":"2401.03038","title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines","created":"2024-01-05","cited_by_count":19,"area":"synth"},{"id":"2506.07949","title":"Cost-Optimal Active AI Model Evaluation","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2406.03339","title":"The Challenges of Evaluating LLM Applications: An Analysis of Automated, Human, and LLM-Based Approaches","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2506.07671","title":"GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation","created":"2025-06-09","cited_by_count":18,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2508.02994","title":"When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs","created":"2025-08-05","cited_by_count":17,"area":"agents"},{"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":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"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":"2409.00009","title":"Web Retrieval Agents for Evidence-Based Misinformation Detection","created":"2024-08-15","cited_by_count":13,"area":"agents"},{"id":"2412.21023","title":"EdgeRAG: Online-Indexed RAG for Edge Devices","created":"2024-12-30","cited_by_count":13,"area":"rag"},{"id":"2511.01758","title":"RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks","created":"2025-11-03","cited_by_count":13,"area":"lr"},{"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":"2412.13102","title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark","created":"2024-12-17","cited_by_count":12,"area":null},{"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":"2402.08277","title":"Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering","created":"2024-02-13","cited_by_count":11,"area":null},{"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":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"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":"2603.20882","title":"RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation","created":"2026-03-21","cited_by_count":11,"area":null},{"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":"2510.11423","title":"Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation","created":"2025-10-13","cited_by_count":10,"area":null},{"id":"2605.19196","title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","created":"2026-05-18","cited_by_count":10,"area":"agents"},{"id":"2506.20051","title":"Controlled Retrieval-augmented Context Evaluation for Long-form RAG","created":"2025-06-24","cited_by_count":9,"area":"rag"},{"id":"2603.27414","title":"Multiple-Prediction-Powered Inference","created":"2026-03-28","cited_by_count":9,"area":null},{"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":"2502.01754","title":"Evaluation of Large Language Models via Coupled Token Generation","created":"2025-02-03","cited_by_count":8,"area":null},{"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":"2509.22957","title":"Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas","created":"2025-09-26","cited_by_count":8,"area":null},{"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":"2511.12920","title":"Auditing Google's AI Overviews and Featured Snippets: A Case Study on Baby Care and Pregnancy","created":"2025-11-17","cited_by_count":7,"area":null},{"id":"2602.17633","title":"When to Trust the Cheap Check: Weak and Strong Verification for Reasoning","created":"2026-02-19","cited_by_count":7,"area":"lr"},{"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":"2606.00093","title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2606.22737","title":"GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation","created":"2026-06-22","cited_by_count":6,"area":"agents"},{"id":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"area":"synth"},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"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":"2409.14744","title":"LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs","created":"2024-09-23","cited_by_count":5,"area":null}],"next_cursor":"100"}