MBZUAI researchers introduce DuwatBench, a new benchmark for multimodal understanding of Arabic calligraphy. The dataset contains 1,272 samples across six calligraphic styles with detailed annotations to evaluate visual-text alignment. Evaluation of 13 multimodal models reveals challenges in processing calligraphic variations and artistic distortions, highlighting the need for culturally grounded AI research.
A national survey in Saudi Arabia of 330 participants reveals that 93% are actively using Generative AI, primarily for text-based tasks, while awareness and understanding remain uneven. Participants recognize benefits like productivity but caution against risks such as privacy, misinformation, and ethical misuse. The study highlights the need for AI literacy, culturally aligned solutions, and stronger frameworks for responsible deployment in Saudi Arabia.
This paper introduces a hybrid deep learning and machine learning pipeline for classifying construction and demolition waste. A dataset of 1,800 images from UAE construction sites was created, and deep features were extracted using a pre-trained Xception network. The combination of Xception features with machine learning classifiers achieved up to 99.5% accuracy, demonstrating state-of-the-art performance for debris identification.
Oman's digital economy investments have reached a significant total of $3.1 billion. This substantial funding is aimed at bolstering various sectors within the digital realm, including technology infrastructure, digital transformation initiatives, and potentially emerging technologies like artificial intelligence. This announcement underscores the Sultanate's strategic focus on developing its non-oil sectors. Why it matters: This considerable investment highlights Oman's commitment to diversifying its economy and fostering a robust digital ecosystem, which is crucial for regional technological advancement and job creation.
This paper introduces an explainable machine learning framework for early-stage chronic kidney disease (CKD) screening, specifically designed for low-resource settings in Bangladesh and South Asia. The framework utilizes a community-based dataset from Bangladesh and evaluates multiple ML classifiers with feature selection techniques. Results show that the ML models achieve high accuracy and sensitivity, outperforming existing screening tools and demonstrating strong generalizability across independent datasets from India, the UAE, and Bangladesh.
The paper introduces Ara-HOPE, a human-centric post-editing evaluation framework for Dialectal Arabic to Modern Standard Arabic (DA-MSA) translation. Ara-HOPE includes a five-category error taxonomy and a decision-tree annotation protocol designed to address the challenges of dialect-specific MT errors. Evaluation of Jais, GPT-3.5, and NLLB-200 shows dialect-specific terminology and semantic preservation remain key challenges. Why it matters: The new framework and public dataset will help improve the evaluation and development of dialect-aware MT systems for Arabic.
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.
A new benchmark, LongShOTBench, is introduced for evaluating multimodal reasoning and tool use in long videos, featuring open-ended questions and diagnostic rubrics. The benchmark addresses the limitations of existing datasets by combining temporal length and multimodal richness, using human-validated samples. LongShOTAgent, an agentic system, is also presented for analyzing long videos, with both the benchmark and agent demonstrating the challenges faced by state-of-the-art MLLMs.
A new study compares vision-language models (VLMs) to YOLOv8 for wastewater treatment plant (WWTP) identification in satellite imagery across the MENA region. VLMs like Gemma-3 demonstrate superior zero-shot performance compared to YOLOv8, trained on a dataset of 83,566 satellite images from Egypt, Saudi Arabia, and UAE. The research suggests VLMs offer a scalable, annotation-free alternative for remote sensing of WWTPs.
The UK-Qatar Joint AI Research Commission, involving institutions such as Queen Mary University of London, has published its final report. This document consolidates findings and recommendations from collaborative research efforts between the United Kingdom and Qatar focused on artificial intelligence. The report signifies the conclusion of a structured initiative aimed at advancing AI knowledge and fostering scientific cooperation between the two nations. Why it matters: This collaboration strengthens international research ties and provides strategic insights that could influence future AI development and policy in Qatar and the wider Middle East.
Saudi Arabia has achieved the 5th position globally in terms of AI sector growth. The Kingdom also leads all other Arab nations in this key measure of artificial intelligence development. This high ranking underscores significant progress and investment within Saudi Arabia's emerging AI ecosystem. Why it matters: This highlights the effective implementation of national AI strategies and sustained investments that are positioning Saudi Arabia as a prominent regional and global player in AI.
Researchers at MBZUAI introduce "Interactive Video Reasoning," a new paradigm enabling models to actively "think with videos" by performing iterative visual actions to gather and refine evidence. They developed Video CoM, which reasons through a Chain of Manipulations (CoM), and constructed Video CoM Instruct, an 18K instruction tuning dataset for multi-step manipulation reasoning. The model is further optimized via reinforcement learning with reasoning aware Group Relative Policy Optimization (GRPO), achieving strong results across nine video reasoning benchmarks.
Researchers at MBZUAI have introduced Video-R2, a reinforcement learning approach to improve the consistency and visual grounding of reasoning in multimodal language models. Video-R2 combines timestamp-aware supervised fine-tuning with Group Relative Policy Optimization (GRPO) guided by a Temporal Alignment Reward (TAR). The model demonstrates higher Think Answer Consistency (TAC), Video Attention Score (VAS), and accuracy across multiple benchmarks, showing improved temporal alignment and reasoning coherence for video understanding.
The paper introduces FanarGuard, a bilingual moderation filter for Arabic and English language models that considers both safety and cultural alignment. A dataset of 468K prompt-response pairs was created and scored by LLM judges on harmlessness and cultural awareness to train the filter. The first benchmark targeting Arabic cultural contexts was developed to evaluate cultural alignment. Why it matters: FanarGuard advances context-sensitive AI safeguards by integrating cultural awareness into content moderation, addressing a critical gap in current alignment techniques.
This paper analyzes the energy consumption and carbon footprint of LLM inference in the UAE compared to Iceland, Germany, and the USA. The study uses DeepSeek Coder 1.3B and the HumanEval dataset to evaluate code generation. It provides a comparative analysis of geographical trade-offs for climate-aware AI deployment, specifically addressing the challenges and potential of datacenters in desert regions.
Researchers at MBZUAI have introduced EvoLMM, a self-evolving framework for large multimodal models that enhances reasoning capabilities without human-annotated data or reward distillation. EvoLMM uses two cooperative agents, a Proposer and a Solver, which generate image-grounded questions and solve them through internal consistency, using a continuous self-rewarding process. Evaluations using Qwen2.5-VL as the base model showed performance gains of up to 3% on multimodal math-reasoning benchmarks like ChartQA, MathVista, and MathVision using only raw training images.
This paper introduces Cross-Document Topic-Aligned (CDTA) chunking to address knowledge fragmentation in Retrieval-Augmented Generation (RAG) systems. CDTA identifies topics across documents, maps segments to topics, and synthesizes them into unified chunks. Experiments on HotpotQA and UAE legal texts show that CDTA improves faithfulness and citation accuracy compared to existing chunking methods, especially for complex queries requiring multi-hop reasoning.
This study compares AI uptake in the UAE and Kuwait, analyzing how constitutional, collective-choice, and operational rules shape AI implementation and its impact on citizen centricity and public value creation. It finds that the UAE's concentrated authority and pro-innovation environment enable scaling AI initiatives, while Kuwait's dispersed governance and cautious approach limit progress despite similar resources. The research highlights the importance of vertical rule coherence over wealth in determining AI's public-value yield.
Microsoft has launched its 'Microsoft Elevate' program in the UAE, an initiative designed to bolster the nation's artificial intelligence ambitions. This program aims to support the development of AI capabilities and foster innovation within the Emirati ecosystem. It likely involves skill development, access to advanced AI tools and infrastructure, and strategic partnerships. Why it matters: This program signifies a major investment by a global technology leader in the UAE's AI future, reinforcing the country's strategic goal to become a leading hub for AI innovation in the Middle East.
A new method is proposed to reduce the verbosity of LLMs in step-by-step reasoning by retaining moderately easy problems during Reinforcement Learning with Verifiable Rewards (RLVR) training. This approach acts as an implicit length regularizer, preventing the model from excessively increasing output length on harder problems. Experiments using Qwen3-4B-Thinking-2507 show the model achieves baseline accuracy with nearly twice shorter solutions.
Gulf countries, particularly Saudi Arabia and the UAE, are strategically investing billions into AI infrastructure, R&D, and talent acquisition to become co-designers of global AI rather than just consumers. This push is driven by sovereign wealth funds, national AI strategies, and a strong political will to diversify economies and achieve digital sovereignty. The region aims to attract top global AI talent and develop models that incorporate diverse ethical frameworks, cultural values, and linguistic specificities, like Arabic. Why it matters: This proactive approach from the Middle East could significantly influence the global AI landscape by fostering a more diverse, ethically nuanced, and culturally relevant design code for future AI systems.
An article published in Nature examines the profound implications of Artificial Intelligence for the workforce within the Gulf Cooperation Council (GCC) countries. It likely delves into the challenges of job displacement and the critical need for reskilling initiatives, alongside the opportunities presented by AI integration across various sectors. The analysis presumably outlines strategies for GCC nations to adapt their labor markets and education systems to the evolving future of work. Why it matters: Understanding these dynamics is crucial for GCC nations to develop effective policies for workforce development, economic resilience, and sustainable growth in an AI-driven era.
MASARAT SA has developed Mubeen, a proprietary Arabic language model specializing in Arabic linguistics, Islamic studies, and cultural heritage. Mubeen was trained using native Arabic sources, including digitized historical manuscripts processed via a proprietary Arabic OCR engine. The model employs a Practical Closure Architecture to improve user intent understanding and provide decisive guidance. Why it matters: Mubeen addresses the utility gap in current Arabic LLMs by focusing on native Arabic data and cultural authenticity, which is critical for heritage preservation and alignment with Saudi Vision 2030.
The UAE has introduced new regulations governing the use of Artificial Intelligence within its national elections. These regulations are designed to enhance transparency and maintain the integrity of the electoral process. The initiative addresses potential applications of AI in electoral contexts to prevent misuse and foster public trust. Why it matters: This development positions the UAE as a leader in establishing frameworks for responsible AI governance in sensitive democratic processes, potentially influencing regional and international discussions on AI ethics in elections.
This survey paper analyzes over 40 benchmarks used to evaluate Arabic large language models, categorizing them into Knowledge, NLP Tasks, Culture and Dialects, and Target-Specific evaluations. It identifies progress in benchmark diversity but also highlights gaps like limited temporal evaluation and cultural misalignment. The paper also examines methods for creating benchmarks, including native collection, translation, and synthetic generation. Why it matters: The survey provides a comprehensive reference for Arabic NLP research and offers recommendations for future benchmark development to better align with cultural contexts.
This paper presents the development and validation of an Arabic version of the Attitudes Toward Large Language Models (AT-GLLM and AT-PLLM) scales, adapted from the original English versions. The study involved translating the scales and testing them on a sample of 249 Arabic-speaking adults. The translated scales demonstrated strong psychometric properties, including a two-factor structure, measurement invariance across genders, and good reliability and validity. Why it matters: This provides a culturally relevant tool for assessing attitudes toward LLMs in the Arab world, crucial for localized research and policy-making in the rapidly growing field of Arabic AI.
Kuwait has successfully conducted the farthest remote robotic surgery, an achievement recognized by Guinness World Records. This pioneering medical procedure showcased advanced capabilities in tele-operation and robotic technology within the healthcare sector. The specific details of the technology used and the medical context were highlighted in the record-setting event. Why it matters: This accomplishment signifies a major leap in medical innovation and remote healthcare capabilities for Kuwait and the broader Middle East region.
Researchers introduce ALARB, a new benchmark for evaluating reasoning in Arabic LLMs using 13K Saudi commercial court cases. The benchmark includes tasks like verdict prediction, reasoning chain completion, and identification of relevant regulations. Instruction-tuning a 12B parameter model on ALARB achieves performance comparable to GPT-4o in verdict prediction and generation.
The study analyzes over 1,000 images generated by ImageFX, DALL-E V3, and Grok for 56 Saudi professions, finding significant gender imbalances and cultural inaccuracies. DALL-E V3 exhibited the strongest gender stereotyping, with 96% male depictions, particularly in leadership and technical roles. The research underscores the need for diverse training data and culturally sensitive evaluation to ensure equitable AI outputs that accurately reflect Saudi Arabia's labor market and culture.
The Hala technical report introduces a family of Arabic-centric instruction and translation models developed using a translate-and-tune pipeline. A strong Arabic-English teacher model is compressed to FP8 and used to create bilingual supervision data. The LFM2-1.2B model is fine-tuned on this data and used to translate English instruction sets into Arabic, creating a million-scale corpus. Why it matters: The release of models, data, evaluation tools, and recipes will accelerate research and development in Arabic NLP, providing valuable resources for the community.
Researchers address the challenge of limited Arabic medical dialogue data by generating 80,000 synthetic question-answer pairs using ChatGPT-4o and Gemini 2.5 Pro, expanding an initial dataset of 20,000 records. They fine-tuned five LLMs, including Mistral-7B and AraGPT2, and evaluated performance using BERTScore and expert review. Results showed that training with ChatGPT-4o-generated data led to higher F1-scores and fewer hallucinations across models. Why it matters: This demonstrates the potential of synthetic data augmentation to improve domain-specific Arabic language models, particularly for low-resource medical NLP applications.
The paper introduces AraHalluEval, a new framework for evaluating hallucinations in Arabic and multilingual large language models (LLMs). The framework uses 12 fine-grained hallucination indicators across generative question answering and summarization tasks, evaluating 12 LLMs including Arabic-specific, multilingual, and reasoning-based models. Results show factual hallucinations are more common than faithfulness errors, with the Arabic model Allam showing lower hallucination rates. Why it matters: This work addresses a critical gap in Arabic NLP by providing a comprehensive tool for assessing and mitigating hallucination in LLMs, which is essential for reliable AI applications in the Arabic-speaking world.
The researchers introduce KAU-CSSL, the first continuous Saudi Sign Language (SSL) dataset focusing on complete sentences. They propose a transformer-based model using ResNet-18 for spatial feature extraction and a Transformer Encoder with Bidirectional LSTM for temporal dependencies. The model achieved 99.02% accuracy in signer-dependent mode and 77.71% in signer-independent mode, advancing communication tools for the SSL community.
This paper introduces AraDhati+, a new comprehensive dataset for Arabic subjectivity analysis created by combining existing datasets like ASTD, LABR, HARD, and SANAD. The researchers fine-tuned Arabic language models including XLM-RoBERTa, AraBERT, and ArabianGPT on AraDhati+ for subjectivity classification. An ensemble decision approach achieved 97.79% accuracy. Why it matters: The work addresses the under-resourced nature of Arabic NLP by providing a new dataset and demonstrating strong results in subjectivity classification, advancing sentiment analysis capabilities for the Arabic language.
Saudi Arabia has launched HUMAIN Chat, a new conversational artificial intelligence application. The platform is being marketed as the first conversational Arabic AI app developed in the region. This launch signifies a key step in the Kingdom's efforts to advance its digital capabilities and AI offerings. Why it matters: The introduction of a dedicated Arabic conversational AI platform can significantly enhance digital interaction for Arabic speakers and accelerate the development of localized AI solutions in the Middle East.
This paper presents a UI-level evaluation of ALLaM-34B, an Arabic-centric LLM developed by SDAIA and deployed in the HUMAIN Chat service. The evaluation used a prompt pack spanning various Arabic dialects, code-switching, reasoning, and safety, with outputs scored by frontier LLM judges. Results indicate strong performance in generation, code-switching, MSA handling, reasoning, and improved dialect fidelity, positioning ALLaM-34B as a robust Arabic LLM suitable for real-world use.
The QU-NLP team presented their approach to the QIAS 2025 shared task on Islamic Inheritance Reasoning, fine-tuning the Fanar-1-9B model using LoRA and integrating it into a RAG pipeline. Their system achieved an accuracy of 0.858 on the final test, outperforming models like GPT 4.5, LLaMA, and Mistral in zero-shot settings. The system particularly excelled in advanced reasoning, achieving 97.6% accuracy. Why it matters: This demonstrates the effectiveness of domain-specific fine-tuning and retrieval augmentation for Arabic LLMs in complex reasoning tasks, even surpassing frontier models.
This paper introduces Saudi-Dialect-ALLaM, a LoRA fine-tuned version of the Saudi Arabian foundation model ALLaM-7B-Instruct-preview, designed to improve the generation of Saudi dialects (Najdi and Hijazi). The model is trained on a private dataset of 5,466 synthetic instruction-response pairs, with two variants explored: Dialect-Token and No-Token training. Results indicate that the Dialect-Token model achieves superior dialect control and fidelity compared to generic instruction models, although the dataset and model weights are not released.
This paper benchmarks the performance of large language models (LLMs) on Arabic medical natural language processing tasks using the AraHealthQA dataset. The study evaluated LLMs in multiple-choice question answering, fill-in-the-blank, and open-ended question answering scenarios. The results showed that a majority voting solution using Gemini Flash 2.5, Gemini Pro 2.5, and GPT o3 achieved 77% accuracy on MCQs, while other LLMs achieved a BERTScore of 86.44% on open-ended questions. Why it matters: The research highlights both the potential and limitations of current LLMs in Arabic clinical contexts, providing a baseline for future improvements in Arabic medical AI.
The UAE government is developing large language models (LLMs) specifically for the Arabic language, with a target training dataset of 20 million words. This initiative aims to overcome the underrepresentation of Arabic in existing AI models. The project seeks to enhance AI's ability to understand and generate nuanced Arabic content. Why it matters: A national Arabic LLM can enable culturally relevant AI applications across various sectors in the region, from education to government services.
Saudi Arabia's national AI authority, SDAIA (Saudi Data and AI Authority), is reportedly developing a National AI Index. This index aims to measure and track the Kingdom's progress and capabilities across various dimensions of artificial intelligence. It is expected to encompass areas such as research and development, talent, infrastructure, and ethical considerations. Why it matters: This initiative provides a crucial framework for evaluating Saudi Arabia's AI ecosystem, guiding future strategic investments, and benchmarking its national AI capabilities against international standards.
Researchers introduce UnsafeChain, a new safety alignment dataset designed to improve the safety of large reasoning models (LRMs) by focusing on 'hard prompts' that elicit harmful outputs. The dataset identifies and corrects unsafe completions into safe responses, exposing models to unsafe behaviors and guiding their correction. Fine-tuning LRMs on UnsafeChain demonstrates enhanced safety and preservation of general reasoning ability compared to existing datasets like SafeChain and STAR-1.
This paper explores Dialectal Arabic (DA) to Modern Standard Arabic (MSA) machine translation using prompting and fine-tuning techniques for Levantine, Egyptian, and Gulf dialects. The study found that few-shot prompting outperformed zero-shot and chain-of-thought methods across six large language models, with GPT-4o achieving the highest performance. A quantized Gemma2-9B model achieved a chrF++ score of 49.88, outperforming zero-shot GPT-4o (44.58). Why it matters: The research provides a resource-efficient pipeline for DA-MSA translation, enabling more inclusive language technologies by addressing the challenges posed by dialectal variations in Arabic.
This paper introduces Absher, a new benchmark for evaluating LLMs' linguistic and cultural competence in Saudi dialects. The benchmark comprises over 18,000 multiple-choice questions spanning six categories, using dialectal words, phrases, and proverbs from various regions of Saudi Arabia. Evaluation of state-of-the-art LLMs reveals performance gaps, especially in cultural inference and contextual understanding, highlighting the need for dialect-aware training.
The authors introduce Nile-Chat, a collection of LLMs (4B, 3x4B-A6B, and 12B) specifically for the Egyptian dialect, capable of understanding and generating text in both Arabic and Latin scripts. A novel language adaptation approach using the Branch-Train-MiX strategy is used to merge script-specialized experts into a single MoE model. Nile-Chat models outperform multilingual and Arabic LLMs like LLaMa, Jais, and ALLaM on newly introduced Egyptian benchmarks, with the 12B model achieving a 14.4% performance gain over Qwen2.5-14B-Instruct on Latin-script benchmarks; all resources are publicly available. Why it matters: This work addresses the overlooked aspect of adapting LLMs to dual-script languages, providing a methodology for creating more inclusive and representative language models in the Arabic-speaking world.
This paper benchmarks reasoning-focused LLMs, especially DeepSeek models, on fifteen Arabic NLP tasks. The study uses zero-shot, few-shot, and fine-tuning strategies. Key findings include that three in-context examples improve F1 scores by over 13 points on classification tasks, DeepSeek outperforms GPT-4-mini by 12 F1 points on complex inference tasks in the zero-shot setting, and LoRA fine-tuning yields up to an additional 8 points in F1 and BLEU. Why it matters: The systematic evaluation provides insights into the performance of LLMs on Arabic NLP, highlighting the effectiveness of different strategies for improving performance and contributing to the development of more capable Arabic language models.
A new benchmark, ViMUL-Bench, is introduced to evaluate video LLMs across 14 languages, including Arabic, with a focus on cultural inclusivity. The benchmark includes 8k manually verified samples across 15 categories and varying video durations. A multilingual video LLM, ViMUL, is also presented, along with a training set of 1.2 million samples, with both to be publicly released.
Researchers from MBZUAI have introduced VideoMolmo, a large multimodal model for spatio-temporal pointing conditioned on textual descriptions. The model incorporates a temporal module with an attention mechanism and a temporal mask fusion pipeline using SAM2 for improved coherence across video sequences. They also curated a dataset of 72k video-caption pairs and introduced VPoS-Bench, a benchmark for evaluating generalization across real-world scenarios, with code and models publicly available.
MBZUAI researchers introduce VideoMathQA, a new benchmark for evaluating mathematical reasoning in videos, requiring models to interpret visual information, text, and spoken cues. The dataset spans 10 mathematical domains with videos ranging from 10 seconds to over 1 hour, and includes multi-step reasoning annotations. The benchmark aims to evaluate temporal cross-modal reasoning and highlights the limitations of existing approaches in complex video-based mathematical problem solving.
This paper introduces a novel evaluation framework for Arabic language models, addressing gaps in linguistic accuracy and cultural alignment. The authors analyze existing datasets and present the Arabic Depth Mini Dataset (ADMD), a curated collection of 490 questions across ten domains. Evaluating GPT-4, Claude 3.5 Sonnet, Gemini Flash 1.5, CommandR 100B, and Qwen-Max using ADMD reveals performance variations, with Claude 3.5 Sonnet achieving the highest accuracy at 30%. Why it matters: The work emphasizes the importance of cultural competence in Arabic language model evaluation, providing practical insights for improvement.