Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zilong, Shen, Xiaoyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908587636293632
author Wang, Zilong
Shen, Xiaoyu
author_facet Wang, Zilong
Shen, Xiaoyu
contents Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that strategically combines OCR engines with Large Language Models (LLMs) to optimize the accuracy-efficiency trade-off inherent in repetitive document extraction tasks. Unlike existing approaches that pursue universal solutions, our method exploits document-specific characteristics through intelligent strategy selection. We implement and evaluate 25 configurations across three extraction paradigms (direct, replacement, and table-based) on identity documents spanning four formats (PNG, DOCX, XLSX, PDF). Through table-based extraction methods, our adaptive framework delivers outstanding results: F1=1.0 accuracy with 0.97s latency for structured documents, and F1=0.997 accuracy with 0.6 s for challenging image inputs when integrated with PaddleOCR, all while maintaining sub-second processing speeds. The 54 times performance improvement compared with multimodal methods over naive approaches, coupled with format-aware routing, enables processing of heterogeneous document streams at production scale. Beyond the specific application to identity extraction, this work establishes a general principle: the repetitive nature of copy-heavy tasks can be transformed from a computational burden into an optimization opportunity through structure-aware method selection.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10138
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task
Wang, Zilong
Shen, Xiaoyu
Computation and Language
Artificial Intelligence
Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that strategically combines OCR engines with Large Language Models (LLMs) to optimize the accuracy-efficiency trade-off inherent in repetitive document extraction tasks. Unlike existing approaches that pursue universal solutions, our method exploits document-specific characteristics through intelligent strategy selection. We implement and evaluate 25 configurations across three extraction paradigms (direct, replacement, and table-based) on identity documents spanning four formats (PNG, DOCX, XLSX, PDF). Through table-based extraction methods, our adaptive framework delivers outstanding results: F1=1.0 accuracy with 0.97s latency for structured documents, and F1=0.997 accuracy with 0.6 s for challenging image inputs when integrated with PaddleOCR, all while maintaining sub-second processing speeds. The 54 times performance improvement compared with multimodal methods over naive approaches, coupled with format-aware routing, enables processing of heterogeneous document streams at production scale. Beyond the specific application to identity extraction, this work establishes a general principle: the repetitive nature of copy-heavy tasks can be transformed from a computational burden into an optimization opportunity through structure-aware method selection.
title Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.10138