{"total":31,"rows":[{"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":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117,"area":"rag"},{"id":"2402.14409","title":"Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models","created":"2024-02-22","cited_by_count":93,"area":"rag"},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2401.08406","title":"RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture","created":"2024-01-16","cited_by_count":81,"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":"2406.14891","title":"Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering","created":"2024-06-21","cited_by_count":51,"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":"2310.03184","title":"Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference","created":"2023-10-04","cited_by_count":38,"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":"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":"2408.15533","title":"LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation","created":"2024-08-28","cited_by_count":17,"area":"rag"},{"id":"2410.01171","title":"Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness","created":"2024-10-02","cited_by_count":14,"area":"rag"},{"id":"2406.18134","title":"Assessing \"Implicit\" Retrieval Robustness of Large Language Models","created":"2024-06-26","cited_by_count":9,"area":"rag"},{"id":"2410.11315","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":9,"area":"rag"},{"id":"2502.08356","title":"Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG","created":"2025-02-12","cited_by_count":9,"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":"2502.18108","title":"Uncertainty Quantification in Retrieval Augmented Question Answering","created":"2025-02-25","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":"2404.10496","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","created":"2024-04-16","cited_by_count":5,"area":"rag"},{"id":"2410.16843","title":"Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning","created":"2024-10-22","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":"2407.10245","title":"GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?","created":"2024-07-14","cited_by_count":3,"area":"rag"},{"id":"2409.10011","title":"HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making","created":"2024-09-16","cited_by_count":3,"area":"rag"},{"id":"2505.03452","title":"An Analysis of Hyper-Parameter Optimization Methods for Retrieval Augmented Generation","created":"2025-05-06","cited_by_count":2,"area":"rag"},{"id":"2503.05530","title":"Leveraging Approximate Caching for Faster Retrieval-Augmented Generation","created":"2025-03-07","cited_by_count":1,"area":"rag"},{"id":"2410.20598","title":"R^3AG: First Workshop on Refined and Reliable Retrieval Augmented Generation","created":"2024-10-27","cited_by_count":0,"area":"rag"},{"id":"2503.16161","title":"Towards Lighter and Robust Evaluation for Retrieval Augmented Generation","created":"2025-03-20","cited_by_count":0,"area":"rag"},{"id":"2508.02872","title":"Highlight & Summarize: RAG without the jailbreaks","created":"2025-08-04","cited_by_count":0,"area":"rag"},{"id":"2610.16008","title":"Improving the Evaluation of Biomedical Question Answering with Few Human Preference Signals","created":"2026-10-12","cited_by_count":0,"area":"rag"}],"next_cursor":null}