{"total":47,"rows":[{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839,"area":"rag"},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312,"area":"rag"},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257,"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":"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":"2408.01262","title":"RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework","created":"2024-08-02","cited_by_count":39,"area":"rag"},{"id":"2409.11242","title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","created":"2024-09-17","cited_by_count":34,"area":"rag"},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25,"area":"rag"},{"id":"2505.04847","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","created":"2025-05-07","cited_by_count":20,"area":"rag"},{"id":"2406.13779","title":"FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering","created":"2024-06-19","cited_by_count":18,"area":"rag"},{"id":"2406.17186","title":"CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation","created":"2024-06-24","cited_by_count":18,"area":"rag"},{"id":"2406.15264","title":"Towards Fine-Grained Citation Evaluation in Generated Text: A Comparative Analysis of Faithfulness Metrics","created":"2024-06-21","cited_by_count":17,"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":"2503.04800","title":"HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation","created":"2025-03-03","cited_by_count":13,"area":"rag"},{"id":"2407.01080","title":"Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese","created":"2024-07-01","cited_by_count":10,"area":"rag"},{"id":"2403.12077","title":"Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions","created":"2024-02-25","cited_by_count":9,"area":"rag"},{"id":"2409.15515","title":"Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA","created":"2024-09-23","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":"2504.15629","title":"CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction","created":"2025-04-22","cited_by_count":8,"area":"rag"},{"id":"2404.07060","title":"Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study","created":"2024-04-10","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":"2411.07773","title":"Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation","created":"2024-11-12","cited_by_count":6,"area":"rag"},{"id":"2504.14856","title":"Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation","created":"2025-04-21","cited_by_count":4,"area":"rag"},{"id":"2512.20182","title":"FaithLens: Detecting and Explaining Faithfulness Hallucination","created":"2025-12-23","cited_by_count":3,"area":"rag"},{"id":"2603.09891","title":"Overview of the TREC 2025 Retrieval Augmented Generation (RAG) Track","created":"2026-03-10","cited_by_count":3,"area":"rag"},{"id":"2408.12398","title":"A Comparative Analysis of Faithfulness Metrics and Humans in Citation Evaluation","created":"2024-08-22","cited_by_count":2,"area":"rag"},{"id":"2410.11217","title":"On the Capacity of Citation Generation by Large Language Models","created":"2024-10-15","cited_by_count":2,"area":"rag"},{"id":"2502.10352","title":"Agentic Verification for Ambiguous Query Disambiguation","created":"2025-02-14","cited_by_count":2,"area":"rag"},{"id":"2508.05366","title":"Can Language Models Critique Themselves? Investigating Self-Feedback for Retrieval Augmented Generation at BioASQ 2025","created":"2025-08-07","cited_by_count":2,"area":"rag"},{"id":"2605.18490","title":"Single-Round Vector RAG vs an LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research Corpus","created":"2026-05-18","cited_by_count":2,"area":"rag"},{"id":"2502.10881","title":"CiteCheck: Towards Accurate Citation Faithfulness Detection","created":"2025-02-15","cited_by_count":1,"area":"rag"},{"id":"2506.22210","title":"UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responses","created":"2025-06-27","cited_by_count":1,"area":"rag"},{"id":"2509.20859","title":"Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation","created":"2025-09-25","cited_by_count":1,"area":"rag"},{"id":"2604.08549","title":"VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering","created":"2026-01-16","cited_by_count":1,"area":"rag"},{"id":"2605.26778","title":"The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context","created":"2026-05-26","cited_by_count":1,"area":"rag"},{"id":"2606.26449","title":"ProvenAI: Provenance-Native Traces of Evidence in Generated Answers","created":"2026-06-24","cited_by_count":1,"area":"rag"},{"id":"2506.22486","title":"Hallucination Detection with Small Language Models","created":"2025-06-24","cited_by_count":0,"area":"rag"},{"id":"2510.20303","title":"Citation Failure: Definition, Analysis and Efficient Mitigation","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2604.06097","title":"Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG","created":"2026-04-07","cited_by_count":0,"area":"rag"},{"id":"2605.29712","title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","created":"2026-05-28","cited_by_count":0,"area":"rag"},{"id":"2606.23915","title":"Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs","created":"2026-06-22","cited_by_count":0,"area":"rag"},{"id":"2606.28358","title":"How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation","created":"2026-06-09","cited_by_count":0,"area":"rag"},{"id":"2607.14400","title":"DS@GT ARC at LongEval: Citation Integrity and Factual Grounding in Scientific QA","created":"2026-07-15","cited_by_count":0,"area":"rag"},{"id":"2608.13410","title":"Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings","created":"2026-08-13","cited_by_count":0,"area":"rag"},{"id":"2608.23252","title":"The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2609.15660","title":"CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense","created":"2026-09-14","cited_by_count":0,"area":"rag"},{"id":"2609.37993","title":"BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals","created":"2026-09-29","cited_by_count":0,"area":"rag"}],"next_cursor":null}