Natural language processing research from GCC institutions, covering Arabic NLP, multilingual models, text classification, named entity recognition, and machine translation.
MBZUAI researchers won second place at the AgentX Competition at UC Berkeley for their benchmark measuring AI agents' reasoning across images, comparisons, and video. The Agent-X dataset includes 828 tasks across six domains, requiring agents to use 14 executable tools without explicit instructions. Agent-X analyzes the agent's full reasoning trajectory, unlike typical evaluations that focus only on final answers. Why it matters: The benchmark exposes limitations in current multimodal AI agents and provides a more rigorous evaluation framework for real-world applications in the region and beyond.
MBZUAI researchers received high honors at EMNLP 2025 for two research papers, placing them in the top 2% of accepted work. One paper, MAviS, is a multimodal AI system that identifies bird species by combining images, sounds, and text. The other award-winning paper focuses on uncertainty in LLM-as-a-Judge. Why it matters: The recognition highlights MBZUAI's growing influence in NLP and multimodal AI research, particularly in domain-specific applications like biodiversity conservation.
MBZUAI researchers have developed MAviS, a new multimodal dataset, benchmark, and chatbot for fine-grained bird species recognition. MAviS includes images, audio, and text to help models identify subtle differences between species, especially rare and regional varieties. The related study was presented at EMNLP 2025 and selected as a "Senior Area Chair Highlight". Why it matters: This work addresses a key limitation in AI's ability to support biodiversity conservation and ecological monitoring in the region and globally.
Google.org is providing $1 million to MBZUAI to fund a research initiative led by Professor Thamar Solorio focused on addressing the “data divide” in AI for underrepresented languages, especially those in the MENA region. The project aims to create resource-lean AI models tailored to the sociocultural and linguistic realities of MENA, requiring less data and computational power. This initiative will also support the training of postdoctoral and early-career researchers at MBZUAI. Why it matters: The funding will help create AI technologies grounded in the linguistic nuances of the MENA region, rather than adapting Western models, while also democratizing AI development by lowering resource requirements.
Researchers from MBZUAI developed "uncertainty quantification heads" (UQ heads) to detect hallucinations in language models by probing internal states and estimating the credibility of generated text. UQ heads leverage attention maps and logits to identify potential hallucinations without altering the model's generation process or relying on external knowledge. The team found that UQ heads achieved state-of-the-art performance in claim-level hallucination detection across different domains and languages. Why it matters: This approach offers a more efficient and accurate method for identifying hallucinations, improving the reliability and trustworthiness of language models in various applications.
MBZUAI faculty member Ekaterina Kochmar and postdoctoral researcher Kaushal Kumar Maurya won a Google Academic Research Award for their research on an intelligent tutoring system. The project, "2σ-ITS," aims to develop an educational foundation model for personalized learning and to support tutors in reaching students with limited access to mainstream education. The Google award provides funding and collaboration opportunities for researchers, with Kochmar and Maurya being the only team from the Middle East to win. Why it matters: This award highlights the growing recognition of AI's potential to improve educational equity and access in the region and beyond.
MBZUAI researchers presented a method for cross-cultural transfer learning to improve language models' understanding of diverse Arab cultures. They used in-context learning and demonstration-based reinforcement (DITTO) to transfer cultural knowledge between countries. Experiments showed up to 34% improvement in performance on cultural understanding benchmarks using only a few demonstrations. Why it matters: This research addresses the gap in cultural understanding of Arabic language models, especially for smaller Arab countries, and provides a novel transfer learning approach.
Researchers from MBZUAI, Carnegie Mellon University, and Meta AI presented a new approach called ThoughtComm at NeurIPS 2025 where AI agents communicate through internal, latent representations instead of natural language. This framework extracts and selectively shares latent "thoughts" from agents' internal states, representing the underlying structure of their reasoning. Results show that agents coordinate more effectively, reach consensus faster, and solve problems more accurately using this method. Why it matters: Bypassing the limitations of natural language in AI communication could lead to more efficient and accurate multi-agent systems, impacting areas like robotics, collaborative AI, and distributed problem-solving.
MBZUAI researchers have introduced SURPRISE3D, a benchmark for evaluating 3D spatial reasoning in AI systems, along with a 3D Spatial Reasoning Segmentation (3D-SRS) task. The benchmark includes over 900 indoor scenes and 200,000 language queries paired with 3D masks, emphasizing spatial relationships over object naming. A companion paper, MLLM-For3D, explores adapting 2D multimodal LLMs for 3D reasoning. Why it matters: This work addresses a key limitation in current AI, pushing towards embodied AI that can understand and act in 3D environments based on human-like spatial reasoning.
MBZUAI has launched master’s and Ph.D. programs in computational biology, expanding its research into life sciences. This includes projects like AIDO (AI-Driven Digital Organism) and analysis of the Emirati Genome Program. The programs are part of MBZUAI’s School of Digital Public Health and aim to integrate computational biology with precision medicine. Why it matters: This initiative supports the UAE's vision for a knowledge-based economy and its ambition to become a global center for scientific and technological progress in biotechnology and healthcare.
MBZUAI researchers presented a NeurIPS 2024 Spotlight paper that quantifies AI vulnerability by measuring bits leaked per query. Their formula predicts the minimum queries needed for attacks based on mutual information between model output and attacker's target. Experiments across seven models and three attack types (system-prompt extraction, jailbreaks, relearning) validate the relationship. Why it matters: This work offers a framework to translate UI choices (like exposing log-probs or chain-of-thought) into concrete attack surfaces, informing more secure AI design and deployment in the region.
MBZUAI Adjunct Professor Iryna Gurevych has won the 2025 Royal Society Milner Award for her contributions to NLP and AI. The Milner Award recognizes outstanding European computer scientists and includes a bronze medal and a £5,000 honorarium. Gurevych's work focuses on processing big data with NLP tools, argument mining, and detecting misleading content. Why it matters: The award highlights MBZUAI's growing prominence in the international AI research landscape and Gurevych's work in making language models safer.
A new paper from MBZUAI demonstrates that state-of-the-art speech models can be easily jailbroken using audio perturbations to generate harmful content, achieving success rates of 76-93% on models like Qwen2-Audio and LLaMA-Omni. The researchers adapted projected gradient descent (PGD) to the audio domain to optimize waveforms that push the model towards harmful responses. They propose a defense mechanism based on post-hoc activation patching that hardens models at inference time without retraining. Why it matters: This research highlights a critical vulnerability in speech-based LLMs and offers a practical solution, contributing to the development of more secure and trustworthy AI systems in the region and globally.
MBZUAI researchers introduced Droid, a resource suite and detector family, at EMNLP 2025 designed to distinguish between AI-generated and human-written code. The project addresses the challenge of identifying AI-generated code in software development, considering the prevalence of AI-suggested code and the risks of obfuscated backdoors and feedback loops. DroidCollection includes over one million code samples across seven programming languages, three coding domains, and outputs from 43 different code models, including human-AI co-authored code and adversarially humanized machine code. Why it matters: This research is crucial for maintaining software security and integrity in the age of AI-assisted coding, providing a robust tool for detecting AI-generated code across diverse languages and domains.
MBZUAI Ph.D. candidate Muhammad Maaz has been awarded the 2025 Google Ph.D. Fellowship in Machine Perception. Maaz is the first student from MBZUAI and the first from the Gulf region to receive this recognition, which includes funding, mentorship, and $50,000. He has published extensively in top-tier CV/NLP venues and has over 4,500 citations. Why it matters: This award highlights the growing prominence of MBZUAI and the increasing quality of AI research in the Gulf region on the global stage.
MBZUAI researchers developed ClinGRAD, a multimodal graph neural network that analyzes genomic data, MRI scans, and clinical information to classify dementia types (Alzheimer's, vascular, etc.). The system addresses the challenge of high misdiagnosis rates (up to 30%) in dementia, where incorrect diagnoses can significantly impact patient life expectancy. ClinGRAD aims to be an interpretable AI system, providing explainability to clinicians. Why it matters: Accurate and early diagnosis of dementia subtypes is crucial for slowing disease progression and improving patient care in the region, where the prevalence of dementia is expected to rise significantly.
MBZUAI researchers Darya Taratynova and Shahad Hardan developed Forget-MI, a method for making clinical AI models "unlearn" specific patient data without retraining the entire model. Forget-MI addresses the challenge of removing patient data from AI models trained on multimodal records (like chest X-rays and reports) due to regulations like GDPR and HIPAA. The method unlearns both unimodal (image or text) and joint (image-text) associations while retaining overall accuracy using a late-fusion multimodal classifier. Why it matters: This research provides a practical solution to a critical privacy concern in healthcare AI, enabling compliance with data protection regulations and fostering trust in AI-driven medical applications.
Researchers at MBZUAI have developed a new automatic method to examine cross-lingual abilities in multilingual language models, testing 10 models across 16 languages. They combined beam search with language-model-based simulation, generating 6,000 bilingual question pairs and found significant performance drops compared to English, even in high-resource languages like Chinese. The method introduces perturbations to test the models' ability to transfer knowledge rather than rely on memorization. Why it matters: This research highlights critical gaps in cross-lingual AI, providing a framework for developing more equitable and effective multilingual models, especially for Arabic and other under-represented languages.
MBZUAI researchers, in collaboration with Monash University, have introduced ArEnAV, a new dataset for deepfake detection featuring Arabic-English code-switching. The dataset comprises 765 hours of manipulated YouTube videos, incorporating intra-utterance code-switching and dialect variations. Experiments showed that code-switching significantly reduces the performance of existing deepfake detectors. Why it matters: This work addresses a critical gap in AI's ability to handle linguistic diversity, particularly in regions where code-switching is prevalent, enhancing the reliability of deepfake detection in real-world scenarios.
Researchers at MBZUAI and other institutions have published a study at ACL 2024 investigating how jailbreak attacks work on LLMs. The study used a dataset of 30,000 prompts and non-linear probing to interpret the effects of jailbreak attacks, finding that existing interpretations were inadequate. The researchers propose a new approach to improve LLM safety against such attacks by identifying the layers in neural networks where the behavior occurs. Why it matters: Understanding and mitigating jailbreak attacks is crucial for ensuring the responsible and secure deployment of LLMs, particularly in the Arabic-speaking world where these models are increasingly being used.
MBZUAI researchers have created ArabCulture, a new benchmark dataset to measure cultural commonsense reasoning capabilities in Arabic language models. The dataset was built by native Arabic speakers from 13 countries and is the largest of its kind. Testing 31 language models, the researchers found that many systems struggle with understanding cultural concepts across the Arab world. Why it matters: The new benchmark addresses a gap in AI, enabling development of culturally-aware AI systems tailored to the nuances of the Arabic-speaking world.
MBZUAI researchers developed FarSight, a plugin to reduce hallucinations in Multimodal Large Language Models (MLLMs). FarSight addresses the issue where MLLMs generate inaccurate text by losing focus on relevant image details, leading to snowball hallucinations. Testing on models like LLaVA-1.5-7B showed FarSight's effectiveness in reducing initial mistakes, thereby minimizing overall hallucinations. Why it matters: Improving the reliability of MLLMs is crucial for applications requiring high accuracy, enhancing their utility in various real-world scenarios.
MBZUAI is conducting research to improve cross-cultural understanding using AI, including studying LLM limitations in recognizing cultural references. They developed "Culturally Yours," a tool that helps users comprehend cultural references in text, and the "All Languages Matter Benchmark" (ALM Bench) to evaluate multimodal LLMs across 100 languages. MBZUAI has also developed LLMs tailored to low-resource languages like Jais (Arabic), Nanda (Hindi), and Sherkala (Kazakh). Why it matters: These initiatives promote inclusivity and ensure AI systems are culturally aware and can serve diverse populations effectively, particularly in the Middle East's multicultural context.
MBZUAI researchers presented FIRE, a new fact-checking framework for LLM outputs, at NAACL 2025. FIRE first assesses the LLM's confidence in its claims before searching the web, reducing computational cost. It also stores knowledge gained from web searches to aid in classifying other claims. Why it matters: This approach improves the efficiency and cost-effectiveness of automatically verifying the accuracy of LLMs, addressing a key limitation in their reliability.
MBZUAI and École Polytechnique are deepening research collaboration through a Collaborative Research Agreement, focusing on large language models, foundation models for reasoning, and AI applications in biology, health, and AI safety. The partnership builds on a previous MoU and Scholars Exchange Program Agreement between the two institutions. MBZUAI's France Lab has developed Atlas-Chat, a family of open-source LLMs for the Moroccan Arabic dialect Darija, with models including Atlas-Chat-2B and Atlas-Chat-9B. Why it matters: This collaboration strengthens the AI ecosystems in both France and the UAE, fostering joint research efforts and supporting the next generation of AI researchers and innovators, with a specific focus on Arabic NLP.
MBZUAI researchers have developed a new benchmark for evaluating the teaching abilities of large language models (LLMs), earning the SAC Award for Resources and Evaluation at NAACL 2025. The framework aims to measure how effectively LLMs can be used for personalized tutoring, addressing the "two sigma problem" in education. Unlike rule-based tutoring systems, LLMs offer fluency but lack pedagogical principles. Why it matters: This benchmark is a crucial step towards integrating learning science into AI, potentially enabling personalized AI tutors that significantly improve educational outcomes.
MBZUAI researchers created a new benchmark dataset called TextGames to evaluate the reasoning abilities of LLMs. The dataset uses simple, text-based games requiring skills like pattern recognition and logical thinking. LLMs struggled with the hardest questions, suggesting limitations in their reasoning capabilities despite advancements in language understanding. Why it matters: This research highlights the need for specialized reasoning models and benchmarks that go beyond memorization to truly test AI's problem-solving abilities.
MBZUAI researchers, in collaboration with over 70 researchers, have created the Culturally diverse Visual Question Answering (CVQA) benchmark to evaluate cultural understanding in multimodal LLMs. The CVQA dataset includes over 10,000 questions in 31 languages and 13 scripts, testing models on images of local dishes, personalities, and monuments. Testing of several multimodal LLMs on the CVQA benchmark revealed significant challenges, even for top models. Why it matters: This benchmark highlights the need for AI models to better understand diverse cultures, promoting fairness and relevance across different languages and regions.
The 31st International Conference on Computational Linguistics (COLING 2025) is being held in Abu Dhabi from January 18-24, hosted by MBZUAI. The conference features paper presentations, demonstrations, keynote speeches, workshops, and tutorials, with over 1,500 attendees. MBZUAI faculty and students contributed 22 papers to the conference, including research on fact-checking and cross-cultural content. Why it matters: Hosting COLING 2025 highlights the UAE's growing role as a hub for AI and NLP research, particularly in Arabic language processing.
MBZUAI researchers have released ALM Bench, a new benchmark dataset for evaluating the performance of multimodal LLMs on cultural visual question-answer tasks across 100 languages. The dataset includes over 22,000 question-answer pairs across 19 categories, with a focus on low-resource languages and cultural nuances, including three Arabic dialects. They tested 16 open- and closed-source multimodal LLMs on it, revealing a significant need for greater cultural and linguistic inclusivity. Why it matters: The benchmark aims to improve the inclusivity of multimodal AI systems by addressing the underrepresentation of low-resource languages and cultural contexts.
This article discusses MBZUAI's efforts in advancing Arabic language AI, including the development of advanced linguistic models using deep learning techniques. Key initiatives include Jais, a 13B parameter Arabic LLM developed in collaboration with G42's Inception, and Atlas-Chat, which understands the Moroccan dialect. The university is also incorporating Arabic in practical AI solutions like BiMediX2, a healthcare multi-modal model that understands medical queries in both English and Arabic. Why it matters: These initiatives are crucial for preserving Arabic cultural heritage, enabling future discovery, and addressing linguistic challenges specific to the Arabic language in AI applications.
MBZUAI researchers introduced Web2Code, a new dataset suite, at NeurIPS to enhance multimodal LLM performance in web page analysis and HTML generation. The suite includes a fine-tuning dataset and two benchmark datasets. Instruction tuning with Web2Code improved performance on specialized tasks without affecting general capabilities. Why it matters: This contribution addresses a key limitation in current multimodal LLMs, potentially boosting productivity in web design and development by providing targeted training data.
Researchers from MBZUAI and King's College London have developed a new prompting strategy called self-guided exploration to improve LLM performance on combinatorial problems. The method was tested on complex challenges like the traveling salesman problem. The findings will be presented at the 38th Annual Conference on Neural Information Processing Systems (NeurIPS) in Vancouver. Why it matters: This research could lead to practical applications of LLMs in industries like logistics, planning, and scheduling by offering new approaches to computationally complex problems.
Researchers at MBZUAI have developed LLM-DetectAIve, a tool to classify the degree of machine involvement in text generation. The system categorizes text into four types: human-written, machine-generated, machine-written and machine-humanized, and human-written and machine-polished. A demo website allows users to test the tool's ability to detect machine involvement. Why it matters: This research addresses the growing need to identify and classify AI-generated content in academic and professional settings, particularly in light of increasing LLM misuse.
A study co-authored by researchers from UC Berkeley, University of the Witwatersrand, Lelapa AI, and MBZUAI received the Outstanding Paper Award at EMNLP 2024. The paper critiques the term "low-resource" languages in NLP, highlighting its limitations in capturing the diverse challenges faced by different languages. The authors propose a more detailed analysis of resourcedness to encourage targeted support for languages currently underserved by technology. Why it matters: The research challenges assumptions in NLP and promotes more nuanced approaches to supporting the world's many languages, including Arabic, in AI systems.
MBZUAI researchers have created ArabicMMLU, the first benchmark dataset in Modern Standard Arabic for evaluating language understanding across multiple tasks. The dataset contains over 14,000 multiple-choice questions from school exams across the Arabic-speaking world and addresses the limitations of translated English datasets. It was presented at the 62nd Annual Meeting of the Association for Computational Linguistics in Bangkok. Why it matters: This benchmark enables a more accurate and culturally relevant evaluation of LLMs' capabilities in Arabic, which is crucial for developing AI tailored to the Arab world.
MBZUAI researchers presented EXAMS-V, a new benchmark dataset for evaluating the reasoning and processing abilities of vision language models (VLMs). EXAMS-V contains over 20,000 multiple-choice questions across 26 subjects and 11 languages, including Arabic. The dataset presents the questions within images, testing the VLM's ability to integrate visual and textual information. Why it matters: This dataset fills a gap in VLM evaluation, providing a valuable resource for assessing and improving the multimodal reasoning capabilities of these models, particularly in diverse languages like Arabic.
MBZUAI published over 300 papers at top-tier AI venues between January and June 2024, including 39 papers at ICLR 2024, building on 612 papers published in 2023. MBZUAI is now ranked among the world's top 100 universities in computer science and top 20 globally in AI-related fields. One standout paper, 'M4,' won the Best Resource Paper Award at EACL 2024 for its work on detecting LLM-generated text across multiple languages and domains. Why it matters: This continued research output and rising rankings solidify MBZUAI's position as a leading AI research institution in the GCC region and globally.
A study by MBZUAI's Preslav Nakov and Cornell co-authors examines how to develop systems that detect fake news in a landscape where text is generated by humans and machines. The research, presented at the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, analyzes fake news detectors' ability to identify human- and machine-written content. The study highlights biases in current detectors, which tend to classify machine-written news as fake and human-written news as true. Why it matters: Addressing these biases is crucial as machine-generated content becomes more prevalent in both real and fake news, requiring more nuanced detection methods.
MBZUAI researchers collaborated with Carnegie Mellon University and the Broad Institute of MIT and Harvard to develop a new statistical method for analyzing data used for gene regulatory network inference. The method addresses the challenge of distinguishing true zero expression values from dropouts in single-cell RNA sequencing data. This research will be presented at the Twelfth International Conference on Learning Representations (ICLR 2024). Why it matters: Improving gene regulatory network inference can lead to better understanding of disease mechanisms and inform the development of new medicines.
MBZUAI researchers are developing spiking neural networks (SNNs) to emulate the energy efficiency of the human brain. Traditional deep learning models like those powering ChatGPT consume significant energy, with a single query using 3.96 watts. SNNs aim to mimic biological neurons more closely to reduce energy consumption, as the human brain uses only a fraction of the energy compared to these models. Why it matters: This research could lead to more sustainable and energy-efficient AI technologies, addressing a major challenge in deploying large-scale AI systems.
MBZUAI faculty and students will present 44 papers at the Empirical Methods in Natural Language Processing (EMNLP) conference in Singapore. Research topics include disinformation detection, social media analysis, dialogue generation, and Arabic LLMs. Preslav Nakov, Iryna Gurevych, Timothy Baldwin, Alham Fikri Aji, and Muhammad Abdul-Mageed are among the MBZUAI researchers presenting at the conference. Why it matters: MBZUAI's strong presence at a top NLP conference highlights the UAE's growing contributions to cutting-edge AI research and its increasing global prominence in the field.
An MBZUAI team won the best paper award at the inaugural Arabic Natural Language Processing Conference for their work on processing Arabic speech. Their study establishes a new approach to tackle the complexities of spoken Arabic, which differs significantly from text-based language models. The team's approach aims to advance new tools for Arabic speakers by addressing challenges like intonation and the continuous nature of speech. Why it matters: This award highlights the importance of specialized research in Arabic NLP, as mainstream LLMs often face limitations in accurately processing the nuances of Arabic speech.
MBZUAI researchers created Bactrian-X, a new dataset to improve LLM instruction following in low-resource languages. The dataset leverages instruction tuning, pairing instructions in various languages with expected responses. Bactrian-X builds upon existing open-source instruction tuning models. Why it matters: This work aims to democratize access to LLMs by enabling users to interact with them in their native languages, even when English proficiency is limited.
MBZUAI faculty and students will present 53 papers at NeurIPS 2023. Key faculty include Eric Xing, Kun Zhang, and Tongliang Liu, each contributing to nine papers. One paper was selected for oral presentation and two for spotlight presentations. Why it matters: MBZUAI's strong presence at NeurIPS highlights its growing influence in the global AI research community and its focus on high-impact AI research.
MBZUAI is a global partner in Meta's release of Llama 2, joining organizations like IBM, AWS, Microsoft, and NVIDIA. MBZUAI will provide early feedback and help build the software as a global community. MBZUAI is working on large language models, developing a sustainable LLM named Vicuna, and strengthening infrastructure for LLM-chat evaluation. Why it matters: MBZUAI's involvement promises to bring about a new generation of UAE-born AI advancements built around the Llama 2 ecosystem and fact-checking capabilities.
MBZUAI is now ranked 24th globally in AI, computer vision, machine learning, and natural language processing, according to CSRankings. This ranking is attributed to the addition of faculty like Preslav Nakov, Hanan Al Darmaki, and Samuel Horvath. MBZUAI now ranks ahead of universities like the University of Michigan and Imperial College London in specific AI fields. Why it matters: This ranking establishes MBZUAI as the top CS institution in the Arab World and highlights the UAE's growing prominence in AI research.
MBZUAI has been ranked 127th globally among institutions conducting computer science research and ranks 30th globally in AI, computer vision, machine learning, and NLP. This places MBZUAI ahead of universities such as the University of Michigan, Georgia Tech, Imperial College London and others. MBZUAI is now the top-ranked CS institution in the Arab World and the Middle East and Africa according to CSRankings. Why it matters: This ranking highlights the rapid growth and increasing prominence of AI research in the UAE and the broader Middle East.
G42's Inception has open-sourced Jais, a 13-billion parameter Arabic large language model (LLM). Jais was trained on a 395-billion-token Arabic and English dataset and outperforms existing Arabic models. The model is a collaboration between Inception, MBZUAI, and Cerebras Systems, and was trained on the Condor Galaxy supercomputer. Why it matters: This release establishes a new standard for Arabic language AI, providing over 400 million Arabic speakers access to generative AI and fostering innovation in the region.
Researchers from MBZUAI, University of British Columbia, and Monash University have created LaMini-LM, a collection of small language models distilled from ChatGPT. LaMini-LM is trained on a dataset of 2.58M instructions and can be deployed on consumer laptops and mobile devices. The smaller models perform almost as well as larger counterparts while addressing security concerns. Why it matters: This work enables the deployment of LLMs in resource-constrained environments and enhances data security by reducing reliance on cloud-based LLMs.