Skip to content
GCC AI Research

Bringing ideas to life with a new writing tool for Arabic language learners

MBZUAI · Notable

Summary

NYU Abu Dhabi and MBZUAI researchers have developed ARWI, a free web application to help Arabic language learners improve their writing skills in Modern Standard Arabic. ARWI provides essay prompts aligned with CEFR skill levels, features an Arabic text editor, and gives personalized feedback. The tool won the Diversity Award at the Workshop on Intelligent and Interactive Writing Assistants (In2Writing). Why it matters: This tool can help preserve the quality and personal voice of Arabic writing amid the rise of LLMs.

Get the weekly digest

Top AI stories from the GCC region, every week.

Related

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion

arXiv ·

This paper introduces AraLLaMA, a new Arabic large language model (LLM) trained using a progressive vocabulary expansion method inspired by second language acquisition. The model utilizes a modified byte-pair encoding (BPE) algorithm to dynamically extend the Arabic subwords in its vocabulary during training, balancing the out-of-vocabulary (OOV) ratio. Experiments show AraLLaMA achieves performance comparable to existing Arabic LLMs on various benchmarks, and all models, data, and code will be open-sourced. Why it matters: This work addresses the need for more accessible and performant Arabic LLMs, contributing to democratization of AI in the Arab world.

Machine learning and natural language processing in support of interactive automated tutoring for non-native

MBZUAI ·

Ted Briscoe from the University of Cambridge discussed using machine learning and NLP to develop learning-oriented assessment (LOA) for non-native writers. The technology is used in Cambridge English courseware like Empower and Linguaskill, as well as Write and Improve. Briscoe is also the co-founder and CEO of iLexIR Ltd. Why it matters: Improving automated language assessment could significantly enhance online language learning platforms in the Arab world and beyond.

ArabianGPT: Native Arabic GPT-based Large Language Model

arXiv ·

The paper introduces ArabianGPT, a suite of transformer-based language models designed specifically for Arabic, including versions with 0.1B and 0.3B parameters. A key component is the AraNizer tokenizer, tailored for Arabic script's morphology. Fine-tuning ArabianGPT-0.1B achieved 95% accuracy in sentiment analysis, up from 56% in the base model, and improved F1 scores in summarization. Why it matters: The models address the gap in native Arabic LLMs, offering better performance on Arabic NLP tasks through tailored architecture and tokenization.

AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3

arXiv ·

The paper introduces AraToken, an Arabic-optimized tokenizer based on the SentencePiece Unigram algorithm that incorporates a normalization pipeline to handle Arabic-specific orthographic variations. Experiments show that AraToken achieves 18% lower fertility compared to unnormalized baselines. The Language Extension Pipeline (LEP) is introduced to integrate AraToken into Qwen3-0.6B, reducing evaluation loss from 8.28 to 2.43 within 800 training steps on 100K Arabic samples. Why it matters: This research provides an efficient tokenizer tailored for Arabic, improving performance of LLMs on Arabic text and benefiting Arabic NLP research by providing released resources.