{"list":"other","total":83,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408},{"id":"2012.09740","title":"Understanding the Behaviour of Contrastive Loss","created":"2020-12-15","cited_by_count":398},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324},{"id":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"2403.18715","title":"Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding","created":"2024-03-27","cited_by_count":203},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114},{"id":"2406.11251","title":"Unifying Multimodal Retrieval via Document Screenshot Embedding","created":"2024-06-17","cited_by_count":110},{"id":"2501.13958","title":"A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models","created":"2025-01-21","cited_by_count":88},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75},{"id":"2411.06037","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","created":"2024-11-09","cited_by_count":72},{"id":"2412.18424","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","created":"2024-12-24","cited_by_count":72},{"id":"2503.13964","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","created":"2025-03-18","cited_by_count":67},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66},{"id":"2404.13948","title":"Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations","created":"2024-04-22","cited_by_count":65},{"id":"2407.10805","title":"Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation","created":"2024-07-15","cited_by_count":64},{"id":"2411.19939","title":"VLSBench: Unveiling Visual Leakage in Multimodal Safety","created":"2024-11-29","cited_by_count":63},{"id":"2002.06071","title":"FQuAD: French Question Answering Dataset","created":"2020-02-14","cited_by_count":58},{"id":"2503.11576","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","created":"2025-03-14","cited_by_count":53},{"id":"2501.00332","title":"MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation","created":"2024-12-31","cited_by_count":44},{"id":"2505.21494","title":"Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment","created":"2025-05-27","cited_by_count":43},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40},{"id":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37},{"id":"2403.12445","title":"Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory","created":"2024-03-19","cited_by_count":36},{"id":"2401.06796","title":"AI Hallucinations: A Misnomer Worth Clarifying","created":"2024-01-09","cited_by_count":34},{"id":"2011.13534","title":"A Survey of Deep Learning Approaches for OCR and Document Understanding","created":"2020-11-27","cited_by_count":32},{"id":"2501.11759","title":"Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems","created":"2025-01-20","cited_by_count":32},{"id":"2504.12330","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","created":"2025-04-13","cited_by_count":31},{"id":"2502.09304","title":"KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG","created":"2025-02-13","cited_by_count":29},{"id":"2506.14035","title":"SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement","created":"2025-06-16","cited_by_count":28},{"id":"2504.10147","title":"A Survey of Personalization: From RAG to Agent","created":"2025-04-14","cited_by_count":27},{"id":"2504.17447","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","created":"2025-04-24","cited_by_count":27},{"id":"2506.04997","title":"Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings","created":"2025-06-05","cited_by_count":26},{"id":"2411.01106","title":"SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding","created":"2024-11-02","cited_by_count":25},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21},{"id":"2506.12364","title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval","created":"2025-06-14","cited_by_count":21},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20},{"id":"2507.14675","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding","created":"2025-07-19","cited_by_count":19},{"id":"2411.02669","title":"Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack","created":"2024-11-04","cited_by_count":18},{"id":"2509.07666","title":"MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval","created":"2025-09-06","cited_by_count":17},{"id":"2505.17471","title":"FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain","created":"2025-05-23","cited_by_count":16},{"id":"2406.04369","title":"RAG Does Not Work for Enterprises","created":"2024-05-31","cited_by_count":15},{"id":"2405.06706","title":"Exploring the Capabilities of Large Multimodal Models on Dense Text","created":"2024-05-09","cited_by_count":14},{"id":"2402.17535","title":"Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control","created":"2024-02-27","cited_by_count":12},{"id":"2508.08589","title":"DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding","created":"2025-08-12","cited_by_count":12},{"id":"2408.00798","title":"Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base","created":"2024-07-20","cited_by_count":11},{"id":"2505.04846","title":"HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights","created":"2025-05-07","cited_by_count":11},{"id":"2508.07313","title":"DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding","created":"2025-08-10","cited_by_count":11},{"id":"2506.20821","title":"MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering","created":"2025-06-25","cited_by_count":9},{"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},{"id":"2508.14066","title":"Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation","created":"2025-08-11","cited_by_count":8},{"id":"2508.17079","title":"Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation","created":"2025-08-23","cited_by_count":6},{"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},{"id":"2507.20145","title":"Multi-Agent Interactive Question Generation Framework for Long Document Understanding","created":"2025-07-27","cited_by_count":4},{"id":"2506.21601","title":"Hierarchical Patch Compression for ColPali: Efficient Multi-Vector Document Retrieval with Dynamic Pruning and Quantization","created":"2025-06-19","cited_by_count":3},{"id":"2509.15432","title":"SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Models","created":"2025-09-18","cited_by_count":3},{"id":"2506.01388","title":"VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding","created":"2025-06-02","cited_by_count":2},{"id":"2508.21024","title":"An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs","created":"2025-08-28","cited_by_count":2},{"id":"2509.09681","title":"DB3 Team's Solution For Meta KDD Cup' 25","created":"2025-08-12","cited_by_count":2}],"next_cursor":null}