Topics ›
Large language models (LLMs) developed, deployed, and researched across the GCC — including Falcon (TII), Jais (MBZUAI/Inception), AceGPT (KAUST), ALLaM (SDAIA), and Fanar (QCRI).
401–450 articles · Page 9 RSS ↗
The first Workshop on Language Models for Low-Resource Languages (LoResLM 2025) was held in Abu Dhabi as part of COLING 2025. It provided a forum for researchers to share work on language models for low-resource languages. The workshop accepted 35 papers from 52 submissions, covering diverse languages and research areas.
This paper explores multilingual satire detection methods in English and Arabic using zero-shot and chain-of-thought (CoT) prompting. It compares the performance of Jais-chat(13B) and LLaMA-2-chat(7B) on distinguishing satire from truthful news. Results show that CoT prompting significantly improves Jais-chat's performance, achieving an F1-score of 80% in English. Why it matters: This demonstrates the potential of Arabic LLMs like Jais to handle nuanced language tasks such as satire detection, which is critical for combating misinformation in the region.
This paper introduces an AI framework for autonomous assessment of student work, addressing policy gaps in academic practices. A survey of 117 academics from the UK, UAE, and Iraq reveals positive attitudes toward AI in education, particularly for autonomous assessment. The study also highlights a lack of awareness of modern AI tools among experienced academics, emphasizing the need for updated policies and training.
Researchers introduce a new task for generating question-passage pairs to aid in developing regulatory question-answering (QA) systems. The ObliQA dataset, comprising 27,869 questions from Abu Dhabi Global Markets (ADGM) financial regulations, is presented. A baseline Regulatory Information Retrieval and Answer Generation (RIRAG) system is designed and evaluated using the RePASs metric.
MBZUAI researchers release LLM-DetectAIve, a tool for fine-grained detection of machine-generated text across four categories: human-written, machine-generated, machine-written then humanized, and human-written then machine-polished. The tool aims to address concerns about misuse of LLMs, especially in education and academia, by identifying attempts to obfuscate or polish content. LLM-DetectAIve is publicly accessible with code and a demonstration video provided.
Google is funding several KAUST research projects with seed grants totaling $100,000. The projects focus on advancing multilingual, multimodal machine learning, particularly in generative and large language models (LLMs). KAUST faculty will conduct research in areas such as health, cross-cultural language understanding, sustainability, privacy, and education. Why it matters: This collaboration signifies growing investment in AI research within Saudi Arabia, fostering innovation and talent development at a leading institution like KAUST.
The fifth Nuanced Arabic Dialect Identification (NADI) 2024 shared task aimed to advance Arabic NLP through dialect identification and dialect-to-MSA machine translation. 51 teams registered, with 12 participating and submitting 76 valid submissions across three subtasks. The winning teams achieved 50.57 F1 for multi-label dialect identification, 0.1403 RMSE for dialectness level identification, and 20.44 BLEU for dialect-to-MSA translation. Why it matters: The results highlight the continued challenges in Arabic dialect processing and provide a benchmark for future research in this area.
The paper addresses the challenge of missing diacritics in Arabic NLP by exploring naturally occurring diacritics in a new dataset across six genres. It maps partially diacritized words to their full diacritization and proposes extensions to the analyze-and-disambiguate approach. The extended diacritization algorithm achieves notable improvements, and the code/datasets are released as open source. Why it matters: This research provides valuable resources and methods for improving Arabic text processing, especially in contexts where diacritization is crucial for accurate interpretation.
arXiv · · Healthcare Research
This paper introduces a method using Stable Diffusion XL (SDXL) fine-tuned with LoRA to generate culturally relevant coloring templates based on Emirati Al-Sadu weaving patterns for mental health therapy. The approach aims to leverage coloring therapy's stress-relieving benefits while embedding cultural resonance, potentially aiding in the treatment of Generalized Anxiety Disorder (GAD). Future research will explore the impact of Emirati heritage art on Emirati individuals using biosignals to assess engagement and effectiveness.
The study introduces AraSpider, the first Arabic version of the Spider dataset, to advance Arabic NLP. Four multilingual translation models and two text-to-SQL models (ChatGPT 3.5 and SQLCoder) were evaluated. Back translation significantly improved the performance of both ChatGPT 3.5 and SQLCoder on the AraSpider dataset. Why it matters: This work democratizes access to text-to-SQL resources for Arabic speakers and provides a methodology for translating datasets to other languages.
The Qatar Computing Research Institute (QCRI) organized a Generative AI Hackathon, showcasing innovative solutions developed by participants. The event brought together students, researchers, and professionals to collaborate on generative AI applications. Participants developed prototypes addressing various societal challenges using cutting-edge AI techniques. Why it matters: This hackathon fosters local AI talent, promotes the application of generative AI to real-world problems in the region, and strengthens Qatar's position in AI innovation.
The Qatar Computing Research Institute (QCRI) recently concluded a Generative AI Hackathon, bringing together participants to innovate with generative artificial intelligence technologies. The event aimed to foster local talent and drive advancements in the field within Qatar. Participants developed various solutions and prototypes using generative AI models and tools. Why it matters: This hackathon signifies Qatar's commitment to cultivating a strong AI ecosystem and developing skilled professionals in cutting-edge AI domains like generative AI.
This research explores the use of generative AI, specifically ChatGPT, to create student assessments that align with academic accreditation standards, such as those of the National Center for Academic Accreditation in Saudi Arabia and ABET. The study introduces a method for mapping verbs used in questions to educational outcomes, enabling AI to produce and validate accreditation-compliant questions. A survey of faculty members in Saudi universities showed high acceptance rates for AI-generated exam questions and AI assistance in editing existing questions.
This paper describes the Nexus team's participation in the ArAIEval shared task focused on detecting propaganda and disinformation in Arabic. The team fine-tuned transformer models and experimented with zero- and few-shot learning using GPT-4. Nexus's system achieved 9th place in subtask 1A and 10th place in subtask 2A. Why it matters: The work contributes to the important goal of automatically identifying and mitigating the spread of disinformation in Arabic content, which is critical for maintaining societal trust and informed public discourse.
The fourth Nuanced Arabic Dialect Identification Shared Task (NADI 2023) aimed to advance Arabic NLP through shared tasks focused on dialect identification and dialect-to-MSA machine translation. 58 teams registered, with 18 participating across three subtasks: dialect identification, dialect-to-MSA translation, and another translation task. The winning teams achieved 87.27 F1 in dialect identification, 14.76 BLEU in one translation task, and 21.10 BLEU in the other. Why it matters: NADI provides valuable benchmarks and datasets for Arabic dialect processing, encouraging further research in this challenging area.
Researchers have introduced LLMeBench, a customizable framework for evaluating large language models (LLMs) across diverse NLP tasks and languages. The framework features generic dataset loaders, multiple model providers, and pre-implemented evaluation metrics, supporting in-context learning with zero- and few-shot settings. LLMeBench was tested on 31 unique NLP tasks using 53 datasets across 90 experimental setups with 296K data points, and the code has been open-sourced. Why it matters: The framework's flexibility and ease of customization should accelerate LLM benchmarking, especially for Arabic and other low-resource languages.
This paper evaluates the performance of GPT-3.5 and GPT-4 on seven Arabic NLP tasks including sentiment analysis, translation, and diacritization. GPT-4 outperforms GPT-3.5 on most tasks. The study provides an analysis of sentiment analysis and introduces a Python interface, Taqyim, for evaluating Arabic NLP tasks. Why it matters: The evaluation of LLMs on Arabic NLP tasks helps to identify strengths and weaknesses, guiding future research and development efforts in the field.
The paper introduces the Unscented Autoencoder (UAE), a novel deep generative model based on the Variational Autoencoder (VAE) framework. The UAE uses the Unscented Transform (UT) for a more informative posterior representation compared to the reparameterization trick in VAEs. It replaces Kullback-Leibler (KL) divergence with the Wasserstein distribution metric and demonstrates competitive performance in Fréchet Inception Distance (FID) scores.
This paper benchmarks the performance of OpenAI's Whisper model on diverse Arabic speech recognition tasks, using publicly available data and novel dialect evaluation sets. The study explores zero-shot, few-shot, and full finetuning scenarios. Results indicate that while Whisper outperforms XLS-R models in zero-shot settings on standard datasets, its performance drops significantly when applied to unseen Arabic dialects.
This paper introduces two shared tasks for abusive and threatening language detection in Urdu, a low-resource language with over 170 million speakers. The tasks involve binary classification of Urdu tweets into Abusive/Non-Abusive and Threatening/Non-Threatening categories, respectively. Datasets of 2400/6000 training tweets and 1100/3950 testing tweets were created and manually annotated, along with logistic regression and BERT-based baselines. 21 teams participated and the best systems achieved F1-scores of 0.880 and 0.545 on the abusive and threatening language tasks, respectively, with m-BERT showing the best performance.
This paper provides an overview of the UrduFake@FIRE2021 shared task, which focused on fake news detection in the Urdu language. The task involved binary classification of news articles into real or fake categories using a dataset of 1300 training and 300 testing articles across five domains. 34 teams registered, with 18 submitting results and 11 providing technical reports detailing various approaches from BoW to Transformer models, with the best system achieving an F1-macro score of 0.679.
This paper presents a comparative study of pre-trained transformer models for Arabic question answering (QA). The study evaluates the performance of AraBERTv2-base, AraBERTv0.2-large, and AraELECTRA models on four reading comprehension datasets: Arabic-SQuAD, ARCD, AQAD, and TyDiQA-GoldP. The researchers fine-tuned these models and analyzed the results to understand the performance disparities. Why it matters: This research contributes to the advancement of Arabic NLP by evaluating and comparing state-of-the-art models on important QA tasks, addressing the scarcity of resources in this domain.
This paper presents team SPPU-AASM's hybrid model for Arabic sarcasm and sentiment detection in the WANLP ArSarcasm shared task 2021. The model combines sentence representations from AraBERT with static word vectors trained on Arabic social media corpora. Results show the system achieves an F1-sarcastic score of 0.62 and a F-PN score of 0.715, outperforming existing approaches. Why it matters: The research demonstrates that combining context-free and contextualized representations improves performance in nuanced Arabic NLP tasks like sarcasm and sentiment analysis.
The Inception Team presented a system for Semantic Question Similarity in Arabic as part of the NSURL 2019 Task 8. The system explores different methods for determining question similarity in Arabic. Their best result was an ensemble model using a pre-trained multilingual BERT model, achieving a 95.924% F1-Score and ranking first among nine participating teams. Why it matters: This demonstrates strong performance on a key Arabic NLP task, advancing the state-of-the-art in semantic understanding for the language.
MBZUAI alumnus Steven Hoang, a 2023 Machine Learning graduate, is now an AI engineer at Wells Fargo, where he contributes to the company's AI strategy. Previously, Hoang worked at AbbVie as a natural language software developer and agentic AI software engineer. Hoang credits his time at MBZUAI for preparing him for this significant role, where he collaborates across departments and considers the broader impact of AI initiatives. Why it matters: This success story highlights MBZUAI's role in developing talent capable of leading AI initiatives at major global financial institutions.
MBZUAI researchers demonstrated a low-latency, multilingual multimodal AI system at GITEX that integrates speech, text, and visual capabilities for more lifelike human-machine conversation. The demo, led by Dr. Hisham Cholakkal, includes a mobile app where users can point their camera at an object and ask questions, receiving spoken answers in multiple languages. They are also integrating the model into a robot dog that can respond to voice commands. Why it matters: This work addresses key challenges in deploying LLMs to real-world applications in the Middle East, such as multilingual support and real-time responsiveness.
MBZUAI student-led startup okkslides, incubated within the University’s Incubation and Entrepreneurship Center (IEC), is developing an AI-native presentation tool. Founded by Lan Wei, a computer science Ph.D. candidate, and Steve Liu, a professor at MBZUAI, okkslides aims to transform messy inputs into executive-grade narratives. The platform focuses on augmenting human reasoning with AI to capture brand nuance and support iterative, human-led collaboration in presentation creation. Why it matters: This highlights the growing entrepreneurial ecosystem at MBZUAI and the potential for AI to improve professional workflows in the region.
MBZUAI President Eric Xing argued at the World Economic Forum in Davos that AI's next phase requires redesigning AI for real-world understanding and uncertainty, rather than just scaling models. He highlighted MBZUAI's unique position in building foundation models from scratch, emphasizing the importance of understanding their nuances, safety, and risks. Xing expressed skepticism about claims of general intelligence in current AI systems, pointing out their fragility and limited form of intelligence. Why it matters: Xing's participation highlights the growing role of Middle Eastern AI institutions like MBZUAI in shaping the global conversation around the future of AI.
MBZUAI · · Finance Healthcare
Dr. Pooja Khosla, formerly an academic, co-founded Entelligent, a climate fintech startup that uses big data and machine learning to help companies manage climate change risk. Khosla recently spoke at MBZUAI, advising academics to translate research into real-world applications, leveraging their unique access to data and analytical thinking. She emphasized the importance of simplifying complex work to make it accessible, noting AI's role in accelerating complex tasks. Why it matters: This highlights the growing trend of translating academic research into practical, impactful business solutions within the AI and climate tech sectors, potentially inspiring more researchers in the region to pursue entrepreneurial ventures.
ElevenLabs, a voice AI research and product company, presented at MBZUAI's Incubation and Entrepreneurship Center (IEC) on the adoption of audio AI in the Middle East. Hussein Makki, general manager for the Middle East at ElevenLabs, highlighted the potential of voice-native AI across sectors like telecommunications, banking, and education. ElevenLabs focuses on making content accessible and engaging across languages and voices through its text-to-speech models. Why it matters: This signals growing interest and investment in voice AI applications within the region, potentially transforming customer service and content accessibility in Arabic.
MBZUAI researchers developed a symbolic adversarial learning framework (SALF) for fake news detection using LLM-powered agents. SALF employs a generator and a detector in a debate-like setup, judged by another LLM, to improve the agents' ability to create and identify fake news. Testing showed that the SALF generator degraded the performance of existing fake news detectors by 53.4% on Chinese and 34.2% on English datasets. Why it matters: This research offers a novel approach to combating the evolving threat of LLM-generated disinformation, a critical issue for maintaining reliable information ecosystems in the region and globally.
MBZUAI Provost Timothy Baldwin predicts that 2025 will be a breakout year for agentic AI, with 33% of enterprise software applications including agentic AI capabilities by 2028. MBZUAI doctoral students Wafa Alghallabi and Omkar Thawaker have launched Lawa.AI, an AI agent being tested on the university's website to provide faster answers and deeper understanding. Lawa.AI evolved from a research project in multimodal efficiency and LLMs and aims to bridge the gap between people and information in higher education and government. Why it matters: This highlights the UAE's focus on translating AI research into practical applications and the growing importance of agentic AI in various sectors.
MBZUAI · · Research Partnership
MBZUAI has launched the K2 Think Hackathon, an international challenge focused on building applications powered by the K2 Think open-source system for advanced reasoning. The hackathon has two stages: a global open call for proposals and an in-person build challenge in Abu Dhabi for the top 10 teams. The winning team's idea will be integrated into the K2 Think app. Why it matters: This hackathon fosters innovation in AI reasoning and provides a platform for developers to create impactful solutions using a system developed in partnership with G42.
MBZUAI · · LLM Partnership
MBZUAI is hosting the K2 Think Hackathon, challenging participants to develop applications using the K2 Think reasoning model developed with G42. The hackathon involves a global idea call followed by a 48-hour build challenge in Abu Dhabi for the top 10 teams. The winning feature will be integrated into the K2 Think application. Why it matters: This hackathon provides a valuable opportunity to test and shape a cutting-edge AI model, potentially leading to innovative applications in various sectors like finance and education within the UAE and beyond.
Nobel laureate Michael Spence lectured at MBZUAI on AI's impact on global economies, focusing on productivity and growth. He highlighted information asymmetries around LLMs and the risk of AI-driven bias in job screening. Spence suggests finding signals that cannot be easily imitated and increase the cost of delivering misleading information. Why it matters: The lecture brings attention to AI's transformative potential and the challenges it poses for economic models and policy in the UAE and globally.
MBZUAI master's graduate Rohit Bharadwaj is pursuing a Ph.D. at the University of Edinburgh, following in the footsteps of Geoffrey Hinton. His research focuses on developing generative models, specifically diffusion models, to anonymize datasets while preserving utility, addressing GDPR compliance. He aims to balance privacy protection with the need for useful data in AI systems. Why it matters: This highlights the growing importance of MBZUAI as a feeder institution for top global AI research programs and the increasing focus on privacy-preserving AI technologies.
MBZUAI graduate Daniel Gebre from Eritrea has developed iShrink, a compression pipeline that reduces the size of LLMs to run offline on mobile phones and edge devices. Gebre's master's thesis focused on enabling access to cutting-edge AI without requiring internet access, motivated by his experience in under-resourced regions. His journey to MBZUAI began with a Merit Scholarship awarded by the UAE Ministry of Education, leading him to pursue a Master of Science in Machine Learning. Why it matters: This research has the potential to democratize access to AI in areas with limited internet connectivity, particularly in regions like Gebre's homeland, Eritrea.
MBZUAI researchers presented a study at ACL 2024 on improving Arabic ASR by pre-training on dialectal Arabic. They trained three versions of the ArTST model: one on MSA, one on MSA and dialectal data, and one on MSA, dialectal, and multilingual data. Results showed that pre-training on dialectal Arabic improves ASR performance across MSA and various dialects. Why it matters: This research addresses a key challenge in Arabic NLP, given the diversity and lack of standardization in dialects, which could lead to more accurate speech recognition systems.
MBZUAI researchers identified 'self-referencing causal cycles' in LLM training data that can mitigate the 'reversal curse,' where LLMs struggle with information presented in reverse order. The study, to be presented at ACL, explains that the transformer architecture's unidirectional token generation causes this issue. By leveraging the repetitive nature of information in training texts, the team developed an efficient solution to improve LLM performance. Why it matters: Overcoming the reversal curse can significantly enhance LLM accuracy and reliability, especially in tasks requiring bidirectional reasoning and understanding of context.
MBZUAI NLP master's graduate Hasan Iqbal developed OpenFactCheck, a framework for fact-checking and evaluating the factual accuracy of large language models. The framework consists of three modules: ResponseEvaluator, LLMEvaluator, and CheckerEvaluator. OpenFactCheck was published at EMNLP 2024 and accepted at NAACL 2025 and COLING 2025, with Iqbal playing an active role at COLING in Abu Dhabi. Why it matters: The development of automated fact-checking frameworks is crucial for ensuring the reliability and trustworthiness of information generated by increasingly prevalent LLMs, especially in the Arabic-speaking world.
Researchers at MBZUAI presented a new Arabic dataset at NAACL to measure LLM safety, building on a Chinese dataset called 'Do Not Answer'. The dataset includes nearly 5,800 questions with challenges and harmless requests containing sensitive terms to test for over-sensitivity. The team localized cultural concepts and added 3,000 questions specific to Arabic language and culture. Why it matters: This comprehensive benchmark, accounting for the diversity of Arabic dialects and cultures, advances the development of safer and more culturally aligned LLMs for Arabic speakers.
MBZUAI researchers presented two studies at NAACL 2025 concerning how LLMs understand cultural differences, with one study winning the SAC award. One study, titled "Reading between the lines: Can LLMs identify cross-cultural communication gaps," assesses GPT-4o's ability to identify cultural references in Goodreads book reviews. The researchers created a benchmark dataset using annotations from 50 evaluators across different cultures to measure the LLM's ability to identify culture-specific items (CSIs). Why it matters: Improving LLMs' cross-cultural understanding is crucial for ensuring these models can be used effectively and equitably across diverse global contexts.
MBZUAI alumnus Hanan Gani, a 2024 master's graduate in machine learning, is now a research associate at MBZUAI working on a meteorological project with the UAE government. He also focuses on multimodal and embodied intelligence research, mentors AI students, and has published nine papers during his time at MBZUAI. His research includes work on vision transformers, text-to-image generation, and large multimodal models. Why it matters: Showcases MBZUAI's role in attracting and developing AI talent within the UAE, contributing to the nation's AI research capabilities.
MBZUAI · · Research Partnership
MBZUAI and UC Berkeley held a joint workshop on machine learning, featuring discussions on online learning, fair allocation in dynamic mechanism design, and causal inference. Michael I. Jordan, Laureate Professor and Honorary Program Director at MBZUAI, highlighted the institute's rapid growth during his visit. Researchers explored methods for enhancing the properties of large, complex models, such as calibration, fairness, and robustness. Why it matters: Such collaborations advance AI research and foster knowledge exchange between leading global experts and regional institutions like MBZUAI.
MBZUAI's Provost, Tim Baldwin, provides six predictions for AI in 2025, highlighting the rise of agentic AI systems capable of performing actions on behalf of users. He notes the recent release of open-weight reasoning models like DeepSeek's R1 and OpenAI's o3-mini, emphasizing the dynamic nature of the field. Baldwin stresses the potential benefits of agentic AI, such as automating complex tasks like travel planning, while also cautioning about the need for careful deployment due to unforeseen outcomes. Why it matters: The predictions provide insight into the near-term trajectory of AI development and deployment, particularly regarding AI agents, and highlights the role of a UAE university in shaping the discussion around AI innovation.
Gregory Chirikjian presented an overview talk on applying probability, harmonic analysis, and geometry to robotics, emphasizing the need for robots to function beyond traditional industrial programming. He discussed a new approach where robots define affordances of objects, using simulation to 'imagine' object use and enabling reasoning about novel objects. Probabilistic methods on Lie-groups, initially developed for mobile robot state estimation, are now adapted for one-shot learning of affordances, with plans to integrate large language models. Why it matters: This research direction aims to enhance robot intelligence and adaptability, crucial for service robots in dynamic environments and aligning with broader goals of advanced AI integration in robotics.
MBZUAI · · Research Healthcare
Researchers at the Rosalind Franklin Institute are using generative AI, including GANs, to augment limited biological datasets, specifically mirtron data from mirtronDB. The synthetic data created mimics real-world samples, facilitating more comprehensive training of machine learning models, leading to improved mirtron identification tools. They also plan to apply Large Language Models (LLMs) to predict unknown patterns in sequence and structure biology problems. Why it matters: This research explores AI techniques to tackle data scarcity in biological research, potentially accelerating discoveries in noncoding RNA and transposable elements.
MBZUAI hosted a talk by Visiting Associate Professor Adrian Bors on continuously streaming AI and the challenge of catastrophic forgetting. The talk covered approaches to continual learning like expanding mixtures of models and generative replay mechanisms. Results were presented on image classification and generation tasks. Why it matters: Continual learning is crucial for AI systems to adapt to new environments and real-world data without forgetting previous knowledge.
Giovanni Puccetti from ISTI-CNR presented research on linguistic probing of language models like BERT and RoBERTa. The research investigates the ability of these models to encode linguistic properties, linking this ability to outlier parameters. Preliminary work on fine-tuning LLMs in Italian and detecting synthetic news generation was also presented. Why it matters: Understanding the inner workings and linguistic capabilities of LLMs is crucial for improving their reliability and adapting them to diverse languages like Arabic.
Niket Tandon from the Allen Institute for AI presented a talk at MBZUAI on enabling large language models to focus on human needs and continuously learn from interactions. He proposed a memory architecture inspired by the theory of recursive reminding to guide models in avoiding past errors. The talk addressed who to ask, what to ask, when to ask and how to apply the obtained guidance. Why it matters: The research explores how to align LLMs with human feedback, a key challenge for practical and ethical AI deployment.