{"total":418,"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":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453,"area":"rag"},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2410.05779","title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","created":"2024-10-08","cited_by_count":315,"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":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"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":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101,"area":"rag"},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83,"area":"rag"},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"area":null},{"id":"2503.21322","title":"HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation","created":"2025-03-27","cited_by_count":68,"area":"rag"},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"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":"2407.08488","title":"Lynx: An Open Source Hallucination Evaluation Model","created":"2024-07-11","cited_by_count":57,"area":"rag"},{"id":"2501.03468","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","created":"2025-01-07","cited_by_count":51,"area":"rag"},{"id":"2503.10150","title":"Retrieval-Augmented Generation with Hierarchical Knowledge","created":"2025-03-13","cited_by_count":47,"area":"rag"},{"id":"2402.03367","title":"RAG-Fusion: a New Take on Retrieval-Augmented Generation","created":"2024-01-31","cited_by_count":42,"area":"rag"},{"id":"2311.08711","title":"PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning","created":"2023-11-15","cited_by_count":39,"area":null},{"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":"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":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"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":"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":"2501.11067","title":"IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems","created":"2025-01-19","cited_by_count":25,"area":"agents"},{"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":"2506.18203","title":"Shrinking the Generation-Verification Gap with Weak Verifiers","created":"2025-06-22","cited_by_count":24,"area":null},{"id":"2504.08758","title":"Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation","created":"2025-03-30","cited_by_count":23,"area":"rag"},{"id":"2401.10036","title":"LOCALINTEL: Generating Organizational Threat Intelligence from Global and Local Cyber Knowledge","created":"2024-01-18","cited_by_count":22,"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":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"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":"2603.03116","title":"Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation","created":"2026-03-03","cited_by_count":20,"area":"agents"},{"id":"2406.05085","title":"Multi-Head RAG: Solving Multi-Aspect Problems with LLMs","created":"2024-06-07","cited_by_count":18,"area":"rag"},{"id":"2504.15800","title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","created":"2025-04-22","cited_by_count":17,"area":"rag"},{"id":"2502.00415","title":"MarketSenseAI 2.0: Enhancing Stock Analysis through LLM Agents","created":"2025-02-01","cited_by_count":16,"area":"agents"},{"id":"2502.10996","title":"RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2407.07858","title":"FACTS About Building Retrieval Augmented Generation-based Chatbots","created":"2024-07-10","cited_by_count":15,"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":"2502.01523","title":"CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering","created":"2025-02-03","cited_by_count":15,"area":null},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2509.26184","title":"Auto-ARGUE: LLM-Based Report Generation Evaluation","created":"2025-09-30","cited_by_count":14,"area":"rag"},{"id":"2603.04474","title":"From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration","created":"2026-03-04","cited_by_count":14,"area":"agents"},{"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":"2405.08120","title":"From Questions to Insightful Answers: Building an Informed Chatbot for University Resources","created":"2024-05-13","cited_by_count":12,"area":"rag"},{"id":"2407.08275","title":"Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems","created":"2024-07-11","cited_by_count":12,"area":"rag"},{"id":"2502.18635","title":"Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems","created":"2025-02-25","cited_by_count":12,"area":"rag"},{"id":"2510.03519","title":"TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2602.10367","title":"LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"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":"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":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2509.04499","title":"DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence","created":"2025-09-02","cited_by_count":10,"area":"agents"},{"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":"2405.06258","title":"Automatic Generation of Model and Data Cards: A Step Towards Responsible AI","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2411.16365","title":"Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines","created":"2024-11-25","cited_by_count":9,"area":"rag"},{"id":"2412.14191","title":"Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2504.06227","title":"LExT: Towards Evaluating Trustworthiness of Natural Language Explanations","created":"2025-04-08","cited_by_count":9,"area":null},{"id":"2509.10858","title":"Large Language Models for Security Operations Centers: A Comprehensive Survey","created":"2025-09-13","cited_by_count":9,"area":null},{"id":"2404.00657","title":"Observations on Building RAG Systems for Technical Documents","created":"2024-03-31","cited_by_count":8,"area":"rag"},{"id":"2407.15748","title":"MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation","created":"2024-07-22","cited_by_count":8,"area":"rag"},{"id":"2409.13694","title":"Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study","created":"2024-09-03","cited_by_count":8,"area":"rag"},{"id":"2502.14864","title":"Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework","created":"2025-02-20","cited_by_count":8,"area":"lr"},{"id":"2504.19101","title":"Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation","created":"2025-04-27","cited_by_count":8,"area":"rag"},{"id":"2506.00789","title":"RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems","created":"2025-06-01","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":"2508.14066","title":"Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation","created":"2025-08-11","cited_by_count":8,"area":"rag"},{"id":"2603.18096","title":"A Trace-Based Assurance Framework for Agentic AI Orchestration: Contracts, Testing, and Governance","created":"2026-03-18","cited_by_count":8,"area":"agents"},{"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":"2403.08607","title":"MedInsight: A Multi-Source Context Augmentation Framework for Generating Patient-Centric Medical Responses using Large Language Models","created":"2024-03-13","cited_by_count":7,"area":null},{"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":"2407.12423","title":"StuGPTViz: A Visual Analytics Approach to Understand Student-ChatGPT Interactions","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2412.15298","title":"A Comparative Study of DSPy Teleprompter Algorithms for Aligning Large Language Models Evaluation Metrics to Human Evaluation","created":"2024-12-19","cited_by_count":7,"area":"alignment"},{"id":"2504.02867","title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications","created":"2025-04-01","cited_by_count":7,"area":"agents"},{"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":"2510.02967","title":"Grounding Large Language Models in Clinical Evidence: A Retrieval-Augmented Generation System for Querying UK NICE Clinical Guidelines","created":"2025-10-03","cited_by_count":7,"area":"rag"},{"id":"2512.08892","title":"Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders","created":"2025-12-09","cited_by_count":7,"area":"rag"},{"id":"2411.07264","title":"Multi-Document Financial Question Answering using LLMs","created":"2024-11-08","cited_by_count":6,"area":null},{"id":"2501.02702","title":"QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance","created":"2025-01-06","cited_by_count":6,"area":"rag"},{"id":"2501.09940","title":"Passage Segmentation of Documents for Extractive Question Answering","created":"2025-01-17","cited_by_count":6,"area":"rag"},{"id":"2502.16573","title":"LawPal : A Retrieval Augmented Generation Based System for Enhanced Legal Accessibility in India","created":"2025-02-23","cited_by_count":6,"area":"rag"},{"id":"2504.02800","title":"Survey and Experiments on Mental Disorder Detection via Social Media: From Large Language Models and RAG to Agents","created":"2025-04-03","cited_by_count":6,"area":"agents"},{"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":"2602.00296","title":"RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing","created":"2026-01-30","cited_by_count":6,"area":"rag"},{"id":"2603.17787","title":"Governed Memory: A Production Architecture for Multi-Agent Workflows","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2603.22651","title":"Benchmarking Multi-Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost-Accuracy Tradeoffs and Production Scaling Strategies","created":"2026-03-24","cited_by_count":6,"area":"agents"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"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":"2403.03888","title":"FaaF: Facts as a Function for the evaluation of generated text","created":"2024-03-06","cited_by_count":5,"area":null},{"id":"2403.15729","title":"Towards a RAG-based Summarization Agent for the Electron-Ion Collider","created":"2024-03-23","cited_by_count":5,"area":"agents"},{"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":"2411.09213","title":"Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering","created":"2024-11-14","cited_by_count":5,"area":"rag"},{"id":"2504.05324","title":"Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2505.12837","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2505.24040","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","created":"2025-05-29","cited_by_count":5,"area":null}],"next_cursor":"100"}