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

arXiv: https://arxiv.org/abs/2607.04636 · HTML: https://mlsanity.com/paper/2607.04636/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 45)

- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [DiT: Self-supervised Pre-training for Document Image Transformer](https://mlsanity.com/paper/2203.02378/) (2022)
- [MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining](https://mlsanity.com/paper/2505.07608/) (2025)
- [SelfDoc: Self-Supervised Document Representation Learning](https://mlsanity.com/paper/2106.03331/) (2021)
- [DocLLM: A layout-aware generative language model for multimodal document understanding](https://mlsanity.com/paper/2401.00908/) (2023)
- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://mlsanity.com/paper/2202.13669/) (2022)
- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [Chargrid: Towards Understanding 2D Documents](https://mlsanity.com/paper/1809.08799/) (2018)
- [StrucTexT: Structured Text Understanding with Multi-Modal Transformers](https://mlsanity.com/paper/2108.02923/) (2021)
- [Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts](https://mlsanity.com/paper/2105.05796/) (2021)
- [CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy](https://mlsanity.com/paper/2412.02210/) (2024)
- [VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2505.22019/) (2025)
- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [Document AI: Benchmarks, Models and Applications](https://mlsanity.com/paper/2111.08609/) (2021)
- [Focus Anywhere for Fine-grained Multi-page Document Understanding](https://mlsanity.com/paper/2405.14295/) (2024)
- [TRIE: End-to-End Text Reading and Information Extraction for Document Understanding](https://mlsanity.com/paper/2005.13118/) (2020)
- [DocILE Benchmark for Document Information Localization and Extraction](https://mlsanity.com/paper/2302.05658/) (2023)
- [olmOCR 2: Unit Test Rewards for Document OCR](https://mlsanity.com/paper/2510.19817/) (2025)
- [Spatial Dual-Modality Graph Reasoning for Key Information Extraction](https://mlsanity.com/paper/2103.14470/) (2021)
- [DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming](https://mlsanity.com/paper/2406.19101/) (2024)
- [CloudScan - A configuration-free invoice analysis system using recurrent neural networks](https://mlsanity.com/paper/1708.07403/) (2017)
- [VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups](https://mlsanity.com/paper/2106.00676/) (2021)
- [Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction](https://mlsanity.com/paper/2310.11016/) (2023)

## Built on by (most cited first, 1 of 1)

- [PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence](https://mlsanity.com/paper/2609.37712/) (2026)

## Abstract (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), while compact locally deployable models lack sufficient KIE supervision. We present SAYRE, a scene-aware document synthesis framework for generating scalable KIE training data without hand-crafted template design. Given a few exemplar documents, SAYRE captures category-specific content patterns and layout conventions to synthesize document-schema-annotation triples. It further introduces error-driven generation, which expands real-world failure cases into hard training examples while preserving their structural patterns. Experiments on constrained- and open-category KIE show that SAYRE consistently improves Qwen3-VL backbones and achieves the strongest overall performance among on-device LMMs. Data scaling experiments show an overall upward trend as more synthesized data is introduced, especially for smaller models and open-category extraction. Error analysis further shows that synthesized training reduces field-level errors by improving schema-aware extraction over dense tables, business identifiers, and contract clauses. These results establish scene-aware synthesis as an effective data-centric approach for improving practical multimodal KIE.