paper-with-me

Papers Key Information Extraction

“Key Information Extraction” 태그가 달린 논문 92편 · 필터 해제

DocClaw: A Unified Agentic System for Intelligent Document Processing

2026-08-19 · Siqi Xiang, Zhipeng Xu, Yufei Liu, Junhao Ji 외 arxiv

Intelligent document processing (IDP) encompasses a broad range of tasks, including optical character recognition (OCR), document question answering (DocQA), and key information extraction (KIE). Despite their distinct o…

Key Information ExtractionQuestion Answering

Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs

2026-08-13 · Beining Xu, Hairui Wang, Jiaxin Wang, Changsheng Chen 외 arxiv

While the privacy risks of multimodal large language models (MLLMs) have drawn significant attention, the unique vulnerabilities of domain-specific MLLMs remain largely underexplored. Focusing on document understanding M…

Key Information Extraction

Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis

2026-07-06 · Zhipeng Xu, Zulong Chen, Qing Liu, Junhao Ji 외 arxiv

Key Information Extraction (KIE) converts visually rich documents into structured data, but practical deployment remains challenging: strong performance often relies on costly on-server Large Multimodal Models (LMMs), wh…

Key Information Extraction

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

2026-07-06 · Abu Tyeb Azad, Ishita Sur Apan, Fahim Ahmed, Sumaiya Karim Katha 외 arxiv

Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in real-world, human-centric applications. However, this adoption is limit…

Key Information ExtractionDocument Layout Analysis

CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing

2026-05-05 · Zhipeng Xu, Junhao Ji, Zulong Chen, Zhenghao Liu 외 arxiv

Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-worl…

Key Information ExtractionQuestion Answering

JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding

2026-03-30 · Koki Maeda, Naoaki Okazaki arxiv

Japanese scene text poses challenges that multilingual benchmarks often fail to capture, including mixed scripts, frequent vertical writing, and a character inventory far larger than the Latin alphabet. Although Japanese…

Key Information ExtractionVisual Question Answering

GLM-OCR Technical Report

2026-03-11 · Shuaiqi Duan, Yadong Xue, Weihan Wang, Zhe Su 외 arxiv

GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a s…

Key Information ExtractionComputational Efficiency

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

2026-03-11 · Daxiang Dong, Mingming Zheng, Dong Xu, Chunhua Luo 외 arxiv

We present Qianfan-OCR, a 4B-parameter end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture. It performs direct image-to-Markdown conver…

Key Information Extraction

DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion

2026-02-25 · Marcel Lamott, Saifullah Saifullah, Nauman Riaz, Yves-Noel Weweler 외 arxiv

Effective document intelligence models rely on large amounts of annotated training data. However, procuring sufficient and high-quality data poses significant challenges due to the labor-intensive and costly nature of da…

Key Information ExtractionDocument Layout AnalysisDocument ClassificationQuestion Answering

UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents

2026-02-03 · Yifan Ji, Zhipeng Xu, Zhenghao Liu, Zulong Chen 외 arxiv

Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Model…

Key Information Extraction

Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs

2026-01-27 · Xinzhong Wang, Ya Guo, Jing Li, Huan Chen 외 arxiv

Key Information Extraction (KIE) from visually-rich documents (VrDs) is a critical task, for which recent Large Language Models (LLMs) and Multi-Modal Large Language Models (MLLMs) have demonstrated strong potential. How…

Key Information Extraction

ROAP: A Reading-Order and Attention-Prior Pipeline for Optimizing Layout Transformers in Key Information Extraction

2026-01-09 · Tingwei Xie, Jinxin He, Yonghong Song arxiv

The efficacy of Multimodal Transformers in visually-rich document understanding (VrDU) is critically constrained by two inherent limitations: the lack of explicit modeling for logical reading order and the interference o…

Key Information Extraction

MMDrive: Interactive Scene Understanding Beyond Vision with Multi-representational Fusion

2025-12-15 · Minghui Hou, Wei-Hsing Huang, Shaofeng Liang, Daizong Liu 외 arxiv

Vision-language models enable the understanding and reasoning of complex traffic scenarios through multi-source information fusion, establishing it as a core technology for autonomous driving. However, existing vision-la…

Key Information ExtractionMultimodal ReasoningScene UnderstandingAutonomous Driving

FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models

2025-10-02 · Karan Dua, Hitesh Laxmichand Patel, Puneet Mittal, Ranjeet Gupta 외 arxiv

Developing document understanding models at enterprise scale requires large, diverse, and well-annotated datasets spanning a wide range of document types. However, collecting such data is prohibitively expensive due to p…

Key Information ExtractionSynthetic Data Generation

SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction

2025-09-27 · Yihao Ding, Soyeon Caren Han, Yanbei Jiang, Yan Li 외 arxiv

Domain-specific Visually Rich Document Understanding (VRDU) presents significant challenges due to the complexity and sensitivity of documents in fields such as medicine, finance, and material science. Existing Large (Mu…

Key Information ExtractionSynthetic Data GenerationDomain Adaptation

AgenticIE: An Adaptive Agent for Information Extraction from Complex Regulatory Documents

2025-09-15 · Gaye Colakoglu, Gürkan Solmaz, Jonathan Fürst arxiv

Declaration of Performance (DoP) documents, mandated by EU regulation, specify characteristics of construction products, such as fire resistance and insulation. While this information is essential for quality control and…

Key Information ExtractionQuestion Answering

Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains

2025-08-26 · Peiran Zhou, Junnan Zhu, Yichen Shen, Ruoxi Yu arxiv

Large Language Models (LLMs) excel in language tasks but are prone to hallucinations and outdated knowledge. Retrieval-Augmented Generation (RAG) mitigates these by grounding LLMs in external knowledge. However, in compl…

Key Information ExtractionQuestion Answering

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization

2025-07-13 · Son Nguyen, Giang Nguyen, Hung Dao, Thao Do 외 arxiv

Key Information Extraction (KIE) underpins the understanding of visual documents (e.g., receipts and contracts) by extracting precise semantic content and accurately capturing spatial structure. Yet existing multimodal l…

Key Information Extraction

PaddleOCR 3.0 Technical Report

2025-07-08 · Cheng Cui, Ting Sun, Manhui Lin, Tingquan Gao 외

This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR…

document understandingKey Information ExtractionOptical Character Recognition (OCR)

Class-Agnostic Region-of-Interest Matching in Document Images

2025-06-26 · Demin Zhang, Jiahao Lyu, Zhijie Shen, Yu Zhou

Document understanding and analysis have received a lot of attention due to their widespread application. However, existing document analysis solutions, such as document layout analysis and key information extraction, ar…

Document Layout Analysisdocument understandingKey Information Extraction
1–20 / 92 다음 →