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

arXiv: https://arxiv.org/abs/2510.10138 · HTML: https://mlsanity.com/paper/2510.10138/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [A Survey on Recent Advances in Named Entity Recognition from Deep Learning models](https://mlsanity.com/paper/1910.11470/) (2019)
- [DocLLM: A layout-aware generative language model for multimodal document understanding](https://mlsanity.com/paper/2401.00908/) (2023)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction](https://mlsanity.com/paper/2203.08411/) (2022)
- [Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction](https://mlsanity.com/paper/2410.21169/) (2024)
- [Self-Prompting Large Language Models for Zero-Shot Open-Domain QA](https://mlsanity.com/paper/2212.08635/) (2022)
- [BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching](https://mlsanity.com/paper/2412.03594/) (2024)
- [A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques](https://mlsanity.com/paper/1707.02919/) (2017)
- [Cross-Domain Learning for Classifying Propaganda in Online Contents](https://mlsanity.com/paper/2011.06844/) (2020)
- [Making Document-Level Information Extraction Right for the Right Reasons](https://mlsanity.com/paper/2110.07686/) (2021)
- [Data-Efficient Information Extraction from Form-Like Documents](https://mlsanity.com/paper/2201.02647/) (2022)
- [Assessing the quality of information extraction](https://mlsanity.com/paper/2404.04068/) (2024)
- [Document Retrieval on Repetitive String Collections](https://mlsanity.com/paper/1605.09362/) (2016)
- [Document Listing on Repetitive Collections with Guaranteed Performance](https://mlsanity.com/paper/1707.06374/) (2017)
- [Fast, Small, and Simple Document Listing on Repetitive Text Collections](https://mlsanity.com/paper/1902.07599/) (2019)
- [End-to-End Document Classification and Key Information Extraction using Assignment Optimization](https://mlsanity.com/paper/2306.00750/) (2023)

## Built on by (most cited first, 5 of 5)

- [Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production](https://mlsanity.com/paper/2605.18818/) (2026)
- [Structured Data Extraction from Real Estate Documents using Clustering, Classification, and Large Language Models](https://mlsanity.com/paper/2607.06012/) (2026)
- [IDP AutoOpt: Agent-Driven Optimization of Document Processing Pipeline Configurations](https://mlsanity.com/paper/2607.26075/) (2026)
- [Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics](https://mlsanity.com/paper/2609.01575/) (2026)
- [Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction](https://mlsanity.com/paper/2609.15706/) (2026)

## Abstract (arXiv)

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.