{"total":20,"rows":[{"id":"2407.13998","title":"RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering","created":"2024-07-19","cited_by_count":43,"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":"2406.16828","title":"Ragnar\\\"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","created":"2024-06-24","cited_by_count":32,"area":"rag"},{"id":"2410.21943","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","created":"2024-10-29","cited_by_count":31,"area":"rag"},{"id":"2409.12558","title":"RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues","created":"2024-09-19","cited_by_count":19,"area":"rag"},{"id":"2410.13716","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","created":"2024-10-17","cited_by_count":14,"area":"rag"},{"id":"2509.10886","title":"CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis","created":"2025-09-13","cited_by_count":6,"area":"rag"},{"id":"2508.05512","title":"RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback","created":"2025-08-07","cited_by_count":5,"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":"2601.16503","title":"MRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine","created":"2026-01-23","cited_by_count":4,"area":"rag"},{"id":"2506.20009","title":"Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks","created":"2025-06-24","cited_by_count":2,"area":"rag"},{"id":"2605.08581","title":"PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design","created":"2026-05-09","cited_by_count":1,"area":"rag"},{"id":"2410.12069","title":"De-jargonizing Science for Journalists with GPT-4: A Pilot Study","created":"2024-10-15","cited_by_count":0,"area":"rag"},{"id":"2504.07584","title":"REANIMATOR: Reanimate Retrieval Test Collections with Extracted and Synthetic Resources","created":"2025-04-10","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":"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":"2512.22629","title":"DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation","created":"2025-12-27","cited_by_count":0,"area":"rag"},{"id":"2605.20729","title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks","created":"2026-05-20","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":"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}