Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy
This work addresses the limitation of existing Document AI frameworks in structurally organizing document information, offering a practical solution for systems dealing with OCRed text, though it is incremental as it builds on synthetic data strategies.
The paper tackles the problem of correcting OCR errors in documents to improve structured information management, proposing the Revise framework which employs a hierarchical error taxonomy and synthetic data generation to train a correction model, resulting in enhanced performance for document retrieval and question answering tasks.
Recent advances in Large Language Models (LLMs) have significantly improved the field of Document AI, demonstrating remarkable performance on document understanding tasks such as question answering. However, existing approaches primarily focus on solving specific tasks, lacking the capability to structurally organize and manage document information. To address this limitation, we propose Revise, a framework that systematically corrects errors introduced by OCR at the character, word, and structural levels. Specifically, Revise employs a comprehensive hierarchical taxonomy of common OCR errors and a synthetic data generation strategy that realistically simulates such errors to train an effective correction model. Experimental results demonstrate that Revise effectively corrects OCR outputs, enabling more structured representation and systematic management of document contents. Consequently, our method significantly enhances downstream performance in document retrieval and question answering tasks, highlighting the potential to overcome the structural management limitations of existing Document AI frameworks.