{"total":20,"rows":[{"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":"2503.00751","title":"RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery","created":"2025-03-02","cited_by_count":19,"area":"rag"},{"id":"2407.02233","title":"Synthetic Multimodal Question Generation","created":"2024-07-02","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":"2506.08074","title":"Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval","created":"2025-06-09","cited_by_count":7,"area":"rag"},{"id":"2409.06595","title":"GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering","created":"2024-09-10","cited_by_count":5,"area":"rag"},{"id":"2603.24579","title":"MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination","created":"2026-03-25","cited_by_count":5,"area":"rag"},{"id":"2410.13671","title":"HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings","created":"2024-10-17","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":"2601.15161","title":"Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation","created":"2026-01-21","cited_by_count":4,"area":"rag"},{"id":"2503.21157","title":"Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?","created":"2025-03-27","cited_by_count":3,"area":"rag"},{"id":"2509.12382","title":"LLM-as-a-Judge: Rapid Evaluation of Legal Document Recommendation for Retrieval-Augmented Generation","created":"2025-09-15","cited_by_count":3,"area":"rag"},{"id":"2509.21336","title":"HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores","created":"2025-09-12","cited_by_count":3,"area":"rag"},{"id":"2509.07706","title":"FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support","created":"2025-09-09","cited_by_count":1,"area":"rag"},{"id":"2509.26011","title":"RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generation","created":"2025-09-30","cited_by_count":1,"area":"rag"},{"id":"2510.18339","title":"ECG-LLM -- training and evaluation of domain-specific large language models for electrocardiography","created":"2025-10-21","cited_by_count":0,"area":"rag"},{"id":"2605.29084","title":"Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG","created":"2026-05-27","cited_by_count":0,"area":"rag"},{"id":"2607.06641","title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","created":"2026-07-07","cited_by_count":0,"area":"rag"},{"id":"2608.21610","title":"Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals","created":"2026-08-21","cited_by_count":0,"area":"rag"}],"next_cursor":null}