paper-with-me

홈 › Papers

RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents

2026-06-05 · Ameya Joshi, Joon Kim, Gus Eggert, Joseph Bajor, Cindy Hao, Jing Reyhan, Kushal Byatnal, Eli Badgio arxiv

Document parsing systems are increasingly deployed in high-stakes, regulated workflows such as mortgage underwriting, financial reporting, supply-chain logistics, and clinical records. Yet most public benchmarks evaluate parsers on clean academic layouts or synthetic prose, and report a single OCR or markdown-level similarity score. Such documents and metrics correlate poorly with what downstream agents actually need: the correct value for a specific field on a messy real-world page. We introduce RealDocBench, a two-track benchmark built from real regulated documents. The QA track contains 1,356 field-level questions over 581 documents spanning four domains, where each question is paired with a typed gold_dict of key-to-value answers and parsers are scored on both per-field and strict per-question accuracy. The layout track contains 1,500 human-verified page images annotated with COCO-style bounding boxes under a nine-class public taxonomy, scored with a Hungarian matcher that includes adjacency-aware split/merge recovery. We evaluate eighteen systems, spanning commercial parsing APIs, general-purpose VLMs, and open-source OCR models, under a uniform extraction-and-scoring protocol, and report accuracy alongside per-page cost and cache-busted latency. RealDocBench exposes a wide performance spread that single-number benchmarks hide, a persistently hard medical sub-domain, and sharp cost/latency trade-offs across operating points. We release the datasets, parser adapters, and evaluation harness to support reproducible, field-level comparison of document parsing systems.

📄 PDF Abstract BibTeX arXiv:2606.07401

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding

2024-04-08 · CVPR 2024 1 · Chuwei Luo, Yufan Shen, Zhaoqing Zhu, Qi Zheng 외

Recently, leveraging large language models (LLMs) or multimodal large language models (MLLMs) for document understanding has been proven very promising. However, previous works that employ LLMs/MLLMs for document underst…

Document AIdocument understanding

FATURA: A Multi-Layout Invoice Image Dataset for Document Analysis and Understanding

2023-11-20 · Mahmoud Limam, Marwa Dhiaf, Yousri Kessentini

Document analysis and understanding models often require extensive annotated data to be trained. However, various document-related tasks extend beyond mere text transcription, requiring both textual content and precise b…

KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document

2025-12-04 · Nimol Thuon, Jun Du arxiv

Automated document layout analysis remains a major challenge for low-resource, non-Latin scripts. Khmer is a language spoken daily by over 17 million people in Cambodia, receiving little attention in the development of d…

Document Layout AnalysisInformation ExtractionDocument AI

Unifying Vision, Text, and Layout for Universal Document Processing

2022-12-05 · CVPR 2023 1 · Zineng Tang, ZiYi Yang, Guoxin Wang, Yuwei Fang 외

We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text, image, and layout modalities together with varied task formats, including document understanding and generation. UDOP le…

Document AIdocument understandingImage ReconstructionVisual Question Answering (VQA)

HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild

2025-12-02 · Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno, Francis Engelmann 외 arxiv

Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and re…

Scene Understanding