Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR
Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for high-resource languages, their performance on Arabic remains limited. In this work, we introduce Baseer, a vision-language model fine-tuned specifically for Arabic document OCR. Leveraging a large-scale dataset combining synthetic and real-world documents, Baseer is trained using a decoder-only fine-tuning strategy to adapt a pre-trained MLLM while preserving general visual features. We also present Misraj-DocOCR, a high-quality, expert-verified benchmark designed for rigorous evaluation of Arabic OCR systems. Our experiments show that Baseer significantly outperforms existing open-source and commercial solutions, achieving a WER of 0.25 and establishing a new state-of-the-art in the domain of Arabic document OCR. Our results highlight the benefits of domain-specific adaptation of general-purpose MLLMs and establish a strong baseline for high-accuracy OCR on morphologically rich languages like Arabic.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction
We present Arabic-Nougat, a suite of OCR models for converting Arabic book pages into structured Markdown text. Based on Meta's Nougat architecture, Arabic-Nougat includes three specialized models: arabic-small-nougat, a…
document understandingOptical Character Recognition (OCR)KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding
With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for E…
document understandingOptical Character RecognitionOptical Character Recognition (OCR)RAG+1Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora
The performance of large language models (LLMs) and large multimodal models (LMMs) depends heavily on the quality and scale of their pre-training datasets. Recent research shows that large multimodal models trained on na…
Fine-Tuning Vision-Language Models for Markdown Conversion of Financial Tables in Malaysian Audited Financial Reports
Accurately extracting and representing the structure of tabular data from financial documents remains a critical challenge in document understanding, particularly for regulatory and analytical use cases. This study addre…
Benchmarking Vision-Language Models for French PDF-to-Markdown Conversion
This report evaluates PDF-to-Markdown conversion using recent Vision-Language Models (VLMs) on challenging French documents. Document parsing is a critical step for Retrieval-Augmented Generation (RAG) pipelines, where t…