{"total":58,"rows":[{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57,"area":null},{"id":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35,"area":"mllm"},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27,"area":null},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2410.21311","title":"MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding","created":"2024-10-25","cited_by_count":19,"area":"mllm"},{"id":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2310.10760","title":"Towards reducing hallucination in extracting information from financial reports using Large Language Models","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2402.03848","title":"ANLS* -- A Universal Document Processing Metric for Generative Large Language Models","created":"2024-02-06","cited_by_count":10,"area":null},{"id":"2404.04003","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","created":"2024-04-05","cited_by_count":8,"area":null},{"id":"2507.09861","title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","created":"2025-07-14","cited_by_count":8,"area":null},{"id":"2406.11403","title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2501.06659","title":"Visual Template Inference for Data Extraction from Documents","created":"2025-01-11","cited_by_count":7,"area":null},{"id":"2407.12358","title":"ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data","created":"2024-07-17","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":"2602.07038","title":"UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2602.15958","title":"DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2410.15484","title":"\"What is the value of {templates}?\" Rethinking Document Information Extraction Datasets for LLMs","created":"2024-10-20","cited_by_count":4,"area":"lr"},{"id":"2507.20145","title":"Multi-Agent Interactive Question Generation Framework for Long Document Understanding","created":"2025-07-27","cited_by_count":4,"area":"agents"},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2603.15118","title":"VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.05150","title":"Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2402.02379","title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2402.05282","title":"TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2405.20245","title":"Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use","created":"2024-05-30","cited_by_count":3,"area":"rag"},{"id":"2502.14918","title":"RAPTOR: Refined Approach for Product Table Object Recognition","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2310.03777","title":"PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2411.03730","title":"NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2412.09341","title":"Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2504.10659","title":"Relation-Rich Visual Document Generator for Visual Information Extraction","created":"2025-04-14","cited_by_count":2,"area":"mllm"},{"id":"2506.14568","title":"QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2510.02133","title":"FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2606.24420","title":"Beyond Logprobs: A Multi-Signal Confidence Engine for LLM-Based Document Field Extraction","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2607.11192","title":"GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2406.08226","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","created":"2024-06-12","cited_by_count":1,"area":"distill"},{"id":"2408.01038","title":"UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2502.06132","title":"Enhancing Document Key Information Localization Through Data Augmentation","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2603.09392","title":"ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2607.04636","title":"Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2607.29677","title":"ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.06607","title":"Pre-Inference Routing for Cost-Efficient Document Field Extraction","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2312.03367","title":"Lazy-k: Decoding for Constrained Token Classification","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2401.09220","title":"UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents","created":"2024-01-17","cited_by_count":0,"area":null},{"id":"2503.16854","title":"Generative Compositor for Few-Shot Visual Information Extraction","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2507.08606","title":"DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2508.13404","title":"TASER: Table Agents for Schema-guided Extraction and Recommendation","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2510.15727","title":"Invoice Information Extraction: Methods and Performance Evaluation","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.09666","title":"Neurosymbolic Information Extraction from Transactional Documents","created":"2025-12-10","cited_by_count":0,"area":"distill"},{"id":"2605.09440","title":"Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.05614","title":"BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2607.14682","title":"Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.01792","title":"Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extraction","created":"2026-08-03","cited_by_count":0,"area":"mllm"},{"id":"2608.14639","title":"Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.16763","title":"LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.30616","title":"OCR-Based Field Extraction for Archaeological Pottery Metadata: The CENTURIA Dataset","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.20110","title":"Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.24092","title":"DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}