Typhoon OCR: Open Vision-Language Model For Thai Document Extraction
On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG
Abstract (arXiv)
Document extraction is a core component of digital workflows, yet existing vision-language models (VLMs) predominantly favor high-resource languages. Thai presents additional challenges due to script complexity from non-latin letters, the absence of explicit word boundaries, and the prevalence of highly unstructured real-world documents, limiting the effectiveness of current open-source models. This paper presents Typhoon OCR, an open VLM for document extraction tailored for Thai and English. The model is fine-tuned from vision-language backbones using a Thai-focused training dataset. The dataset is developed using a multi-stage data construction pipeline that combines traditional OCR, VLM-based restructuring, and curated synthetic data. Typhoon OCR is a unified framework capable of text transcription, layout reconstruction, and document-level structural consistency. The latest iteration of our model, Typhoon OCR V1.5, is a compact and inference-efficient model designed to reduce reliance on metadata and simplify deployment. Comprehensive evaluations across diverse Thai document categories, including financial reports, government forms, books, infographics, and handwritten documents, show that Typhoon OCR achieves performance comparable to or exceeding larger frontier proprietary models, despite substantially lower computational cost. The results demonstrate that open vision-language OCR models can achieve accurate text extraction and layout reconstruction for Thai documents, reaching performance comparable to proprietary systems while remaining lightweight and deployable.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 10 of its 19 references that are in the map. First posted on arXiv 21 Jan 2026.
Builds on
10 of 19 references.
Closest ancestors · 1
Same direction, newest first
Other references · 9
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
- 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
- 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 146
- 2025Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generationcited by 54
- 2023PyThaiNLP: Thai Natural Language Processing in Pythoncited by 27
- 2022Augraphy: A Data Augmentation Library for Document Imagescited by 14
- 2025ChartCap: Mitigating Hallucination of Dense Chart Captioningcited by 7
- 2022OCR Improves Machine Translation for Low-Resource Languagescited by 5
- 2025ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thaicited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026How Far Can Synthetic Data Take Thai OCR?cited by 0
- 2026How Far Can Synthetic Data Take Thai OCR?3 Sep 2026
Similar, not cited
Close in wording, no citation either way
- 2024Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
- 2026OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets
- 2026Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application
- 2026Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction
- 2026Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
- 2025dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model
- 2025Evaluating Multimodal Large Language Models on Vertically Written Japanese Text
- 2024Building and better understanding vision-language models: insights and future directions