{"total":85,"rows":[{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452,"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":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341,"area":null},{"id":"2407.01284","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","created":"2024-07-01","cited_by_count":286,"area":"lr"},{"id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195,"area":"mllm"},{"id":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125,"area":"mllm"},{"id":"2305.13269","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","created":"2023-05-22","cited_by_count":122,"area":null},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83,"area":"rag"},{"id":"2403.05313","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","created":"2024-03-08","cited_by_count":75,"area":"lr"},{"id":"2411.02937","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","created":"2024-11-05","cited_by_count":65,"area":"mllm"},{"id":"2503.04812","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","created":"2025-03-04","cited_by_count":55,"area":null},{"id":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48,"area":"lr"},{"id":"2405.20204","title":"Jina CLIP: Your CLIP Model Is Also Your Text Retriever","created":"2024-05-30","cited_by_count":46,"area":null},{"id":"2410.08182","title":"MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models","created":"2024-10-10","cited_by_count":42,"area":"rag"},{"id":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2511.00405","title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings","created":"2025-11-01","cited_by_count":38,"area":"lr"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2309.08872","title":"PDFTriage: Question Answering over Long, Structured Documents","created":"2023-09-16","cited_by_count":29,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2404.19543","title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","created":"2024-04-30","cited_by_count":25,"area":"rag"},{"id":"2405.17980","title":"Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering","created":"2024-05-28","cited_by_count":25,"area":null},{"id":"2410.13360","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models","created":"2024-10-17","cited_by_count":24,"area":"mllm"},{"id":"2311.07536","title":"A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering","created":"2023-11-13","cited_by_count":23,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2409.09916","title":"SFR-RAG: Towards Contextually Faithful LLMs","created":"2024-09-16","cited_by_count":19,"area":"rag"},{"id":"2402.07658","title":"The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models","created":"2024-02-12","cited_by_count":18,"area":null},{"id":"2412.17759","title":"Survey of Large Multimodal Model Datasets, Application Categories and Taxonomy","created":"2024-12-23","cited_by_count":17,"area":"mllm"},{"id":"2501.15795","title":"Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?","created":"2025-01-27","cited_by_count":17,"area":"mllm"},{"id":"2409.17073","title":"Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2503.06254","title":"Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation","created":"2025-03-08","cited_by_count":12,"area":"lr"},{"id":"2405.04533","title":"ChatHuman: Chatting about 3D Humans with Tools","created":"2024-05-07","cited_by_count":11,"area":null},{"id":"2409.10955","title":"Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style","created":"2024-09-17","cited_by_count":11,"area":"rag"},{"id":"2505.04846","title":"HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights","created":"2025-05-07","cited_by_count":11,"area":"rag"},{"id":"2412.20927","title":"Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering","created":"2024-12-30","cited_by_count":10,"area":"mllm"},{"id":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2406.03776","title":"XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags","created":"2024-06-06","cited_by_count":9,"area":null},{"id":"2503.04790","title":"SuperRAG: Beyond RAG with Layout-Aware Graph Modeling","created":"2025-02-28","cited_by_count":9,"area":"rag"},{"id":"2510.15253","title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","created":"2025-10-17","cited_by_count":9,"area":"rag"},{"id":"2407.02233","title":"Synthetic Multimodal Question Generation","created":"2024-07-02","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":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2404.12720","title":"PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering","created":"2024-04-19","cited_by_count":7,"area":null},{"id":"2505.06020","title":"ArtRAG: Retrieval-Augmented Generation with Structured Context for Visual Art Understanding","created":"2025-05-09","cited_by_count":7,"area":"rag"},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2601.03979","title":"SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems","created":"2026-01-07","cited_by_count":7,"area":"rag"},{"id":"2408.03562","title":"A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use Case","created":"2024-08-07","cited_by_count":6,"area":"rag"},{"id":"2502.14930","title":"RAGVA: Engineering Retrieval Augmented Generation-based Virtual Assistants in Practice","created":"2025-02-20","cited_by_count":6,"area":"rag"},{"id":"2505.11815","title":"UniMoCo: Unified Modality Completion for Robust Multi-Modal Embeddings","created":"2025-05-17","cited_by_count":5,"area":"mllm"},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2410.02296","title":"How to Make LMs Strong Node Classifiers?","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2410.11321","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":4,"area":"rag"},{"id":"2504.07643","title":"CollEX -- A Multimodal Agentic RAG System Enabling Interactive Exploration of Scientific Collections","created":"2025-04-10","cited_by_count":4,"area":"rag"},{"id":"2607.01243","title":"STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2409.15815","title":"AsthmaBot: Multi-modal, Multi-Lingual Retrieval Augmented Generation For Asthma Patient Support","created":"2024-09-24","cited_by_count":3,"area":"rag"},{"id":"2412.16701","title":"AlzheimerRAG: Multimodal Retrieval Augmented Generation for Clinical Use Cases using PubMed articles","created":"2024-12-21","cited_by_count":3,"area":"rag"},{"id":"2603.00511","title":"Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning","created":"2026-02-28","cited_by_count":3,"area":"rag"},{"id":"2402.11203","title":"Exploring ChatGPT for Next-generation Information Retrieval: Opportunities and Challenges","created":"2024-02-17","cited_by_count":2,"area":null},{"id":"2403.09567","title":"Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models","created":"2024-03-14","cited_by_count":2,"area":"agents"},{"id":"2508.17215","title":"How to make Medical AI Systems safer? Simulating Vulnerabilities, and Threats in Multimodal Medical RAG System","created":"2025-08-24","cited_by_count":2,"area":"mllm"},{"id":"2510.09266","title":"CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation","created":"2025-10-10","cited_by_count":2,"area":"mllm"},{"id":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2604.24564","title":"MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG","created":"2026-04-27","cited_by_count":2,"area":"mllm"},{"id":"2605.11864","title":"Very Efficient Listwise Multimodal Reranking for Long Documents","created":"2026-05-12","cited_by_count":2,"area":"rag"},{"id":"2305.03025","title":"Panda LLM: Training Data and Evaluation for Open-Sourced Chinese Instruction-Following Large Language Models","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2405.11397","title":"Preparing for Black Swans: The Antifragility Imperative for Machine Learning","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2408.10264","title":"Order-Preserving Dimension Reduction for Multimodal Semantic Embedding","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2409.13732","title":"Enhancing Large Language Models with Domain-Specific Knowledge: The Case in Topological Materials","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2410.13037","title":"LFOSum: Summarizing Long-form Opinions with Large Language Models","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2503.02589","title":"MCiteBench: A Multimodal Benchmark for Generating Text with Citations","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2504.06138","title":"Multimedia and Visual Analytics in the Agentic Era","created":"2025-04-08","cited_by_count":1,"area":"agents"},{"id":"2507.22933","title":"Augmented Vision-Language Models: A Systematic Review","created":"2025-07-24","cited_by_count":1,"area":"mllm"},{"id":"2508.08816","title":"Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2509.19980","title":"RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis","created":"2025-09-24","cited_by_count":1,"area":"rag"},{"id":"2510.22694","title":"Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation","created":"2025-10-26","cited_by_count":1,"area":"mllm"},{"id":"2512.05959","title":"M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG","created":"2025-12-05","cited_by_count":1,"area":"mllm"},{"id":"2601.04571","title":"Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.15487","title":"MiRAGE: A Multiagent Framework for Generating Multimodal Multihop Question-Answer Dataset for RAG Evaluation","created":"2026-01-21","cited_by_count":1,"area":"rag"},{"id":"2604.19689","title":"A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding","created":"2026-04-21","cited_by_count":1,"area":"agents"},{"id":"2606.01120","title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2403.10798","title":"Object Retrieval for Visual Question Answering with Outside Knowledge","created":"2024-03-16","cited_by_count":0,"area":"rag"},{"id":"2506.09247","title":"Agent-based Condition Monitoring Assistance with Multimodal Industrial Database Retrieval Augmented Generation","created":"2025-06-10","cited_by_count":0,"area":"rag"},{"id":"2608.23176","title":"Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2608.27466","title":"PACE: Publisher-Adaptive Content Extraction via Agentic Automation","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2609.26056","title":"CricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching","created":"2026-08-08","cited_by_count":0,"area":"mllm"},{"id":"2610.03421","title":"CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}