{"total":24,"rows":[{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116,"area":null},{"id":"2309.10952","title":"LMDX: Language Model-based Document Information Extraction and Localization","created":"2023-09-19","cited_by_count":37,"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":"2409.19672","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","created":"2024-09-29","cited_by_count":12,"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":"2602.12247","title":"ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction","created":"2026-02-12","cited_by_count":9,"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":"2501.03403","title":"BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations","created":"2025-01-06","cited_by_count":8,"area":null},{"id":"2408.06345","title":"Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2502.18179","title":"Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs","created":"2025-02-25","cited_by_count":6,"area":null},{"id":"2405.00505","title":"KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents","created":"2024-05-01","cited_by_count":5,"area":null},{"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":"2403.20101","title":"RealKIE: Five Novel Datasets for Enterprise Key Information Extraction","created":"2024-03-29","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":"2602.12203","title":"ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2608.06607","title":"Pre-Inference Routing for Cost-Efficient Document Field Extraction","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2405.16728","title":"Towards Multi-Task Multi-Modal Models: A Video Generative Perspective","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2509.23273","title":"SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction","created":"2025-09-27","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":"2609.02207","title":"LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images","created":"2026-09-02","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":"2609.22620","title":"Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.23679","title":"Mind the Gaps: A Curated Benchmark for Form Field Detection","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.31341","title":"The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}