Abstract
Retrieving accurate details from documents is a crucial task, especially when handling a combination of scanned images and native digital formats. This document presents a combined framework for text extraction that merges Optical Character Recognition (OCR) techniques with Large Language Models (LLMs) to deliver structured outputs enriched by contextual understanding and confidence indicators. Scanned files are processed using OCR engines, while digital files are interpreted through layout-aware libraries. The extracted raw text is subsequently analyzed by an LLM to identify key-value pairs and resolve ambiguities. A comparative analysis of different OCR tools is presented to evaluate their effectiveness concerning accuracy, layout recognition, and processing speed. The approach demonstrates significant improvements over traditional rule-based and template-based methods, offering enhanced flexibility and semantic precision across different document categories
Abstract (translated)
从文档中准确提取细节是一项至关重要的任务，特别是在处理扫描图像和原生数字格式的组合时。本文提出了一种结合框架，将光学字符识别（OCR）技术与大型语言模型（LLMs）相结合，以提供由上下文理解和置信度指标增强的结构化输出。扫描文件通过OCR引擎进行处理，而数字文件则通过布局感知库来解释。提取的原始文本随后由LLM分析，以识别键值对并解决歧义问题。本文还提供了不同OCR工具的比较分析，评估它们在准确性、布局识别和处理速度方面的效果。该方法相较于传统的基于规则的方法和基于模板的方法展示了显著改进，提供增强的灵活性和语义精确度，适用于不同的文档类别。
URL
https://arxiv.org/abs/2506.11156
