{"total":79,"rows":[{"id":"2411.04952","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","created":"2024-11-07","cited_by_count":111,"area":"rag"},{"id":"2406.04744","title":"CRAG -- Comprehensive RAG Benchmark","created":"2024-06-07","cited_by_count":97,"area":"rag"},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77,"area":"rag"},{"id":"2403.03187","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","created":"2024-03-05","cited_by_count":73,"area":"rag"},{"id":"2301.07094","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","created":"2023-01-17","cited_by_count":58,"area":"rag"},{"id":"2501.05874","title":"VideoRAG: Retrieval-Augmented Generation over Video Corpus","created":"2025-01-10","cited_by_count":57,"area":"rag"},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51,"area":"rag"},{"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":"2412.10704","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":41,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2505.16470","title":"Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering","created":"2025-05-22","cited_by_count":36,"area":"rag"},{"id":"2503.18016","title":"Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook","created":"2025-03-23","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":"2501.18365","title":"RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects","created":"2025-01-30","cited_by_count":27,"area":"rag"},{"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":"2504.20734","title":"UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities","created":"2025-04-29","cited_by_count":20,"area":"rag"},{"id":"2504.14493","title":"FinSage: A Multi-aspect RAG System for Financial Filings Question Answering","created":"2025-04-20","cited_by_count":19,"area":"rag"},{"id":"2502.14727","title":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","created":"2025-02-20","cited_by_count":18,"area":"rag"},{"id":"2505.18543","title":"Benchmarking Poisoning Attacks against Retrieval-Augmented Generation","created":"2025-05-24","cited_by_count":18,"area":"rag"},{"id":"2502.04176","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","created":"2025-02-06","cited_by_count":15,"area":"rag"},{"id":"2410.09942","title":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","created":"2024-10-13","cited_by_count":14,"area":"rag"},{"id":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"id":"2412.16500","title":"Speech Retrieval-Augmented Generation without Automatic Speech Recognition","created":"2024-12-21","cited_by_count":14,"area":"rag"},{"id":"2412.21023","title":"EdgeRAG: Online-Indexed RAG for Edge Devices","created":"2024-12-30","cited_by_count":13,"area":"rag"},{"id":"2502.16641","title":"Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines","created":"2025-02-23","cited_by_count":13,"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":"2406.19150","title":"RAVEN: Multitask Retrieval Augmented Vision-Language Learning","created":"2024-06-27","cited_by_count":10,"area":"rag"},{"id":"2411.16365","title":"Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines","created":"2024-11-25","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":"2504.02132","title":"One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image","created":"2025-04-02","cited_by_count":8,"area":"rag"},{"id":"2510.15261","title":"AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory","created":"2025-10-17","cited_by_count":8,"area":"rag"},{"id":"2405.13127","title":"Towards Retrieval-Augmented Architectures for Image Captioning","created":"2024-05-21","cited_by_count":7,"area":"rag"},{"id":"2510.07233","title":"LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding","created":"2025-10-08","cited_by_count":7,"area":"rag"},{"id":"2410.09699","title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","created":"2024-10-13","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":"2505.13957","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5,"area":"rag"},{"id":"2408.05933","title":"Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models","created":"2024-08-12","cited_by_count":4,"area":"rag"},{"id":"2410.11321","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":4,"area":"rag"},{"id":"2511.00903","title":"ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval","created":"2025-11-02","cited_by_count":4,"area":"rag"},{"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":"2501.11929","title":"ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation","created":"2025-01-21","cited_by_count":3,"area":"rag"},{"id":"2510.02388","title":"Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation","created":"2025-09-30","cited_by_count":3,"area":"rag"},{"id":"2601.17644","title":"Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks","created":"2026-01-25","cited_by_count":3,"area":"rag"},{"id":"2602.13239","title":"CrisiSense-RAG: Crisis Sensing Multimodal Retrieval-Augmented Generation for Rapid Disaster Impact Assessment","created":"2026-01-30","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":"2306.01061","title":"Reimagining Retrieval Augmented Language Models for Answering Queries","created":"2023-06-01","cited_by_count":2,"area":"rag"},{"id":"2504.04065","title":"Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answering","created":"2025-04-05","cited_by_count":2,"area":"rag"},{"id":"2511.04080","title":"Caption Injection for Optimization in Generative Search Engine","created":"2025-11-06","cited_by_count":2,"area":"rag"},{"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":"2606.26458","title":"MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation","created":"2026-06-24","cited_by_count":2,"area":"rag"},{"id":"2504.02894","title":"OnRL-RAG: Real-Time Personalized Mental Health Dialogue System","created":"2025-04-02","cited_by_count":1,"area":"rag"},{"id":"2506.10030","title":"Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment","created":"2025-06-10","cited_by_count":1,"area":"rag"},{"id":"2509.02123","title":"CMRAG: Co-modality-based visual document retrieval and question answering","created":"2025-09-02","cited_by_count":1,"area":"rag"},{"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":"2602.13179","title":"Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation","created":"2026-02-13","cited_by_count":1,"area":"rag"},{"id":"2603.26046","title":"Retrieval-Augmented Generation Based Nurse Observation Extraction","created":"2026-03-27","cited_by_count":1,"area":"rag"},{"id":"2605.13277","title":"Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation","created":"2026-05-13","cited_by_count":1,"area":"rag"},{"id":"2605.15019","title":"From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG","created":"2026-05-14","cited_by_count":1,"area":"rag"},{"id":"2607.05438","title":"Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG","created":"2026-07-03","cited_by_count":1,"area":"rag"},{"id":"2607.24861","title":"HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document","created":"2026-07-26","cited_by_count":1,"area":"rag"},{"id":"2608.24977","title":"Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation","created":"2026-08-25","cited_by_count":1,"area":"rag"},{"id":"2412.11396","title":"Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes","created":"2024-12-16","cited_by_count":0,"area":"rag"},{"id":"2504.07794","title":"Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generation","created":"2025-04-10","cited_by_count":0,"area":"rag"},{"id":"2505.18450","title":"BRIT: Bidirectional Retrieval over Unified Image-Text Graph","created":"2025-05-24","cited_by_count":0,"area":"rag"},{"id":"2510.17354","title":"Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation","created":"2025-10-20","cited_by_count":0,"area":"rag"},{"id":"2512.17194","title":"MMRAG-RFT: Two-stage Reinforcement Fine-tuning for Explainable Multi-modal Retrieval-augmented Generation","created":"2025-12-19","cited_by_count":0,"area":"rag"},{"id":"2603.23989","title":"CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction","created":"2026-03-25","cited_by_count":0,"area":"rag"},{"id":"2604.05268","title":"Region-R1: Reinforcing Query-Side Region Cropping for Multi-Modal Re-Ranking","created":"2026-04-07","cited_by_count":0,"area":"rag"},{"id":"2605.10253","title":"Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation","created":"2026-05-11","cited_by_count":0,"area":"rag"},{"id":"2606.03354","title":"ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation","created":"2026-06-02","cited_by_count":0,"area":"rag"},{"id":"2606.26916","title":"PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation","created":"2026-06-25","cited_by_count":0,"area":"rag"},{"id":"2607.22643","title":"Reason Before You Retrieve: Agentic Planning for Multi-modal RAG","created":"2026-06-24","cited_by_count":0,"area":"rag"},{"id":"2608.14032","title":"HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation","created":"2026-08-14","cited_by_count":0,"area":"rag"},{"id":"2608.16536","title":"DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption","created":"2026-08-17","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":"2609.14685","title":"ViTeGate: Visual-Textual Triggered Knowledge Poisoning for Vision-Language Retrieval-Augmented Generation","created":"2026-09-13","cited_by_count":0,"area":"rag"},{"id":"2609.37349","title":"TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG","created":"2026-09-29","cited_by_count":0,"area":"rag"}],"next_cursor":null}