Researchers from MBZUAI have introduced UrduFactCheck, a new framework for fact-checking in Urdu, along with two datasets: UrduFactBench and UrduFactQA. The framework uses monolingual and translation-based evidence retrieval to address the lack of Urdu resources. Evaluations using twelve LLMs showed that translation-augmented methods improve performance, highlighting challenges for open-source LLMs in Urdu.
MBZUAI researchers introduce FAID, a fine-grained AI-generated text detection framework capable of classifying text as human-written, LLM-generated, or collaboratively written. FAID utilizes multi-level contrastive learning and multi-task auxiliary classification to capture authorship and model-specific characteristics, and can identify the underlying LLM family. The framework outperforms existing baselines, especially in generalizing to unseen domains and new LLMs, and includes a multilingual, multi-domain dataset called FAIDSet.
Saudi health innovators are increasing investment in smart health solutions, using KAUST's infrastructure and expertise. The King Salman Center for Disability Research (KSCDR) and KCSH are partnering on AI-based methods to identify genetic causes of rare eye diseases. KAUST and the Saudi Food and Drug Administration (SFDA) are expanding their agreement to enhance cooperation on AI and digital innovation. Why it matters: These partnerships signal a concerted effort to leverage AI for addressing critical healthcare challenges and advancing the Kingdom's health priorities.
This paper introduces DaringFed, a novel dynamic Bayesian persuasion pricing mechanism for online federated learning (OFL) that addresses the challenge of two-sided incomplete information (TII) regarding resources. It formulates the interaction between the server and clients as a dynamic signaling and pricing allocation problem within a Bayesian persuasion game, demonstrating the existence of a unique Bayesian persuasion Nash equilibrium. Evaluations on real and synthetic datasets demonstrate that DaringFed optimizes accuracy and convergence speed and improves the server's utility.
KAUST researchers have discovered the first molecular events that trigger wheat's immunity to stem rust, a devastating fungal disease. The study, published in Science, identifies that tandem kinases are bound together and inactive until a pathogen binds, initiating an immune response that kills the infected cell. This prevents the pathogen from spreading and causing widespread crop damage. Why it matters: Understanding these molecular mechanisms could lead to engineering wheat with stronger and more durable resistance to stem rust and other diseases, safeguarding a crucial food source in the face of climate change and emerging pathogens.
This paper introduces SemDiff, a novel method for generating unrestricted adversarial examples (UAEs) by exploring the semantic latent space of diffusion models. SemDiff uses multi-attribute optimization to ensure attack success while preserving the naturalness and imperceptibility of generated UAEs. Experiments on high-resolution datasets demonstrate SemDiff's superior performance compared to state-of-the-art methods in attack success rate and imperceptibility, while also evading defenses.
The paper introduces SaudiCulture, a new benchmark for evaluating the cultural competence of LLMs within Saudi Arabia, covering five major geographical regions and diverse cultural domains. The benchmark includes questions of varying complexity and distinguishes between common and specialized regional knowledge. Evaluations of five LLMs (GPT-4, Llama 3.3, FANAR, Jais, and AceGPT) revealed performance declines on region-specific questions, highlighting the need for region-specific knowledge in LLM training.
This paper introduces the AI Pentad model, comprising humans/organizations, algorithms, data, computing, and energy, as a framework for AI regulation. It also presents the CHARME²D Model to link the AI Pentad with regulatory enablers like registration, monitoring, and enforcement. The paper assesses AI regulatory efforts in the EU, China, UAE, UK, and US using the CHARME²D model, highlighting strengths and weaknesses.
A new survey paper provides a deep dive into post-training methodologies for Large Language Models (LLMs), analyzing their role in refining LLMs beyond pretraining. It addresses key challenges such as catastrophic forgetting, reward hacking, and inference-time trade-offs, and highlights emerging directions in model alignment, scalable adaptation, and inference-time reasoning. The paper also provides a public repository to continually track developments in this fast-evolving field.
Researchers introduce TimeTravel, a benchmark dataset for evaluating large multimodal models (LMMs) on historical and cultural artifacts. The benchmark comprises 10,250 expert-verified samples across 266 cultures and 10 historical regions, designed to assess AI in tasks like classification and interpretation of manuscripts, artworks, inscriptions, and archaeological discoveries. The goal is to establish AI as a reliable partner in preserving cultural heritage and assisting researchers.
This research evaluates LLMs like ChatGPT, Llama, Aya, Jais, and ACEGPT on Arabic automated essay scoring (AES) using the AR-AES dataset. The study uses zero-shot, few-shot learning, and fine-tuning approaches while using a mixed-language prompting strategy. ACEGPT performed best among the LLMs with a QWK of 0.67, while a smaller BERT model achieved 0.88. Why it matters: The study highlights challenges faced by LLMs in processing Arabic and provides insights into improving LLM performance in Arabic NLP tasks.
The paper introduces VENOM, a text-driven framework for generating high-quality unrestricted adversarial examples using diffusion models. VENOM unifies image content generation and adversarial synthesis into a single reverse diffusion process, enhancing both attack success rate and image quality. The framework incorporates an adaptive adversarial guidance strategy with momentum to ensure the generated adversarial examples align with the distribution of natural images.
Researchers at MBZUAI have demonstrated a method called "Data Laundering" to artificially boost language model benchmark scores using knowledge distillation. The technique covertly transfers benchmark-specific knowledge, leading to inflated accuracy without genuine improvements in reasoning. The study highlights a vulnerability in current AI evaluation practices and calls for more robust benchmarks.
Saudi Arabia has announced the establishment of a new International Water Research Center in partnership between the Ministry of Environment, Water and Agriculture and KAUST. The center will serve as a global platform for applied water research, addressing water economics, security, pollution, and digital monitoring. Headquartered at KAUST, the center seeks to foster national and international cooperation, leveraging KAUST's resources to develop sustainable solutions for water challenges. Why it matters: This initiative signals Saudi Arabia's commitment to addressing critical water challenges and solidifying its leadership in water research and technology within the region.
KAUST researchers have identified a gene, CLAMT1b, in pearl millet that affects its vulnerability to the parasitic weed Striga hermonthica. Pearl millet strains lacking CLAMT1b were found to be resistant to the weed, while those expressing the gene were susceptible. The gene's presence leads to the secretion of strigolactones, promoting interaction with Striga, but its absence does not harm symbiotic relationships with beneficial fungi. Why it matters: This discovery offers new breeding strategies to enhance pearl millet's resistance to parasitic weeds, bolstering food security in arid regions like Saudi Arabia and Africa where the crop is vital.
Researchers introduce ArabLegalEval, a multitask benchmark dataset for assessing Arabic legal knowledge in LLMs. The dataset contains tasks sourced from Saudi legal documents and synthesized questions, drawing inspiration from MMLU and LegalBench. Experiments benchmarked models including GPT-4 and Jais, exploring in-context learning and various evaluation methods. Why it matters: This resource should help accelerate AI research and evaluation in the Arabic legal domain, where datasets are lacking.
MBZUAI researchers release OpenFactCheck, a unified framework to evaluate the factual accuracy of large language models. The framework includes modules for response evaluation, LLM evaluation, and fact-checker evaluation. OpenFactCheck is available as an open-source Python library, a web service, and via GitHub.
This survey paper reviews recent literature on continual learning in medical imaging, addressing challenges like catastrophic forgetting and distribution shifts. It covers classification, segmentation, detection, and other tasks, while providing a taxonomy of studies and identifying challenges. The authors also maintain a GitHub repository to keep the survey up-to-date with the latest research.
A study compared the vulnerability of C programs generated by nine state-of-the-art Large Language Models (LLMs) using a zero-shot prompt. The researchers introduced FormAI-v2, a dataset of 331,000 C programs generated by these LLMs, and found that at least 62.07% of the generated programs contained vulnerabilities, detected via formal verification. The research highlights the need for risk assessment and validation when deploying LLM-generated code in production environments.
KAUST researchers have developed a green synthetic biology approach using engineered algae to replicate the complex fragrances of agarwood, also known as oudh. They catalogued the chemical diversity of sesquiterpenes (STPs) in 58 agarwood samples and reproduced some of the chemical complexity of agarwood STPs in algae using synthetic biology. The team used the green alga Chlamydomonas reinhardtii to produce nine distinct STP chemical products widely found in agarwood, offering a sustainable alternative to harvesting endangered trees. Why it matters: This research provides a sustainable route for producing sought-after fragrances, reducing pressure on endangered agarwood tree populations and promoting green chemistry in the region.
This paper explores the impact of tokenization strategies and vocabulary sizes on Arabic language model performance across NLP tasks like news classification and sentiment analysis. It compares four tokenizers, finding that Byte Pair Encoding (BPE) with Farasa performs best overall due to its morphological analysis capabilities. The study surprisingly found limited impact of vocabulary size on performance with fixed model sizes, challenging assumptions about vocabulary size and model performance. Why it matters: The findings provide insights for developing more effective and nuanced Arabic language models, particularly for handling dialectal variations and promoting responsible AI development in the region.
The paper introduces AraTrust, a new benchmark for evaluating the trustworthiness of LLMs when prompted in Arabic. The benchmark contains 522 multiple-choice questions covering dimensions like truthfulness, ethics, safety, and fairness. Experiments using AraTrust showed that GPT-4 performed the best, while open-source models like AceGPT 7B and Jais 13B had lower scores. Why it matters: This benchmark addresses a critical gap in evaluating LLMs for Arabic, which is essential for ensuring the safe and ethical deployment of AI in the Arab world.
KAUST researchers have developed a new synthetic biology process using metabolically engineered algae to produce fragrant sesquiterpenoids, the core compounds in agarwood and other perfumes. The process, developed by the Lauersen and Szekely groups, achieved yields 25 times higher than previous methods and allows for the synthesis of 103 types of fragrant sesquiterpenoids. It also incorporates an energy-efficient nanofiltration step and operates at room temperature with minimal waste. Why it matters: This sustainable bioprocess offers a green alternative to environmentally damaging harvesting of natural resources for the $44 billion fragrance industry, with potential applications in drug development.
This paper investigates the intrinsic self-correction capabilities of LLMs, identifying model confidence as a key latent factor. Researchers developed an "If-or-Else" (IoE) prompting framework to guide LLMs in assessing their own confidence and improving self-correction accuracy. Experiments demonstrate that the IoE-based prompt enhances the accuracy of self-corrected responses, with code available on GitHub.
Researchers propose a universal anatomical embedding (UAE) framework for medical image analysis to learn appearance, semantic, and cross-modality anatomical embeddings. UAE incorporates semantic embedding learning with prototypical contrastive loss, a fixed-point-based matching strategy, and an iterative approach for cross-modality embedding learning. The framework was evaluated on landmark detection, lesion tracking and CT-MRI registration tasks, outperforming existing state-of-the-art methods.
Researchers from KAUST, King Faisal Specialist Hospital, and collaborators have developed a new method to predict cardiometabolic disease risk in underrepresented ethnic populations using genetic information and public databases. The study focused on Arab communities and created a framework to determine polygenic scores for more accurate heart disease prediction. The framework was validated using records of over 5,000 Arab patients, demonstrating that genetic risk complements conventional risk factors. Why it matters: This research addresses a critical gap in genomic data for non-European populations, potentially leading to more effective and personalized healthcare strategies in the Arab world and beyond.
Researchers introduce AceGPT, a localized large language model (LLM) specifically for Arabic, addressing cultural sensitivity and local values not well-represented in mainstream models. AceGPT incorporates further pre-training with Arabic texts, supervised fine-tuning using native Arabic instructions and GPT-4 responses, and reinforcement learning with AI feedback using a reward model attuned to local culture. Evaluations demonstrate that AceGPT achieves state-of-the-art performance among open Arabic LLMs across several benchmarks. Why it matters: This work advances culturally-aware AI development for Arabic-speaking communities, providing a valuable resource and benchmark for future research.
MBZUAI researchers introduce M4, a multi-generator, multi-domain, and multi-lingual benchmark dataset for detecting machine-generated text. The study reveals challenges in generalizing detection across unseen domains or LLMs, with detectors often misclassifying machine-generated text as human-written. The dataset aims to foster research into more robust detection methods and is available on GitHub.
This paper introduces ProgramFC, a fact-checking model that decomposes complex claims into simpler sub-tasks using a library of functions. The model uses LLMs to generate reasoning programs and executes them by delegating sub-tasks, enhancing explainability and data efficiency. Experiments on fact-checking datasets demonstrate ProgramFC's superior performance compared to baseline methods, with publicly available code and data.
KAUST and King Faisal Specialist Hospital and Research Centre (KFSH&RC) are collaborating to develop bioelectronic sensors for rapid pathogen detection. These sensors aim to provide cheap and accurate results, potentially replacing conventional lab tests. A COVID-19 saliva test developed by KAUST researchers showed comparable sensitivity to PCR tests with a 15-minute turnaround. Why it matters: This partnership accelerates the development of novel diagnostic tools, which could improve healthcare accessibility in remote areas and low-income countries within the region.
This paper introduces Provable Unrestricted Adversarial Training (PUAT), a novel adversarial training approach. PUAT enhances robustness against both unrestricted and restricted adversarial examples while improving standard generalizability by aligning the distributions of adversarial examples, natural data, and the classifier's learned distribution. The approach uses partially labeled data and an augmented triple-GAN to generate effective unrestricted adversarial examples, demonstrating superior performance on benchmarks.
The paper introduces LLMEffiChecker, a tool to test the computational efficiency robustness of LLMs by identifying vulnerabilities that can significantly degrade performance. LLMEffiChecker uses both white-box (gradient-guided perturbation) and black-box (causal inference-based perturbation) methods to delay the generation of the end-of-sequence token. Experiments on nine public LLMs demonstrate that LLMEffiChecker can substantially increase response latency and energy consumption with minimal input perturbations.
Researchers at KAUST and international collaborators have published a framework in Nature Microbiology for using microbiomes to protect wildlife. The framework outlines a path from laboratory research to large-scale applications of microbiome solutions for threatened ecosystems. It addresses ethical considerations and risk assessment for applying environmental probiotics. Why it matters: This framework provides a science-based guide for responsible research and development of microbiome solutions to combat global biodiversity loss, particularly in sensitive marine ecosystems like coral reefs.
KAUST and AlFaisal University have signed an MOU to establish a joint M.D.-Ph.D. program, the first of its kind in Saudi Arabia. AlFaisal medical students selected for the program will enroll in a KAUST Ph.D. program focused on basic research, smart-health tools, and precision medicine. Graduates will become clinician-scientists implementing smart-health methods in the Saudi healthcare system. Why it matters: This program will cultivate a new generation of leaders in smart health and precision medicine, fostering evidence-based practices in Saudi healthcare.
Researchers at KAUST and Peking University Third Hospital have created a novel blastoid model for studying early human development using extended pluripotent stem cells (EPSCs). The blastoid is a 3D cell model mimicking the blastocyst phase, avoiding ethical concerns associated with using human embryos. The team showed that blastoids can be cultured to mimic post-implantation development, offering insights into early cell lineages. Why it matters: This innovation provides a way to study human embryogenesis without the ethical constraints of using actual embryos, potentially advancing our understanding of miscarriage and birth defects.
A KAUST-led study published in Science found overwhelming evidence that man-made noise negatively impacts marine fauna and their ecosystems, disrupting behavior, physiology, and reproduction. The researchers assessed over 10,000 papers to demonstrate that noise pollution from shipping, fishing, and infrastructure development harms marine life from invertebrates to whales. They call for human-induced noise to be considered a prevalent stressor at the global scale and for policy to be developed to mitigate its effects. Why it matters: This research highlights the need to consider acoustic dimensions in ocean health restoration efforts, promoting management actions to reduce noise levels and allow marine animals to re-establish their use of ocean sound.
Khaled Alsayegh at the King Abdullah International Medical Research Center is creating a Saudi Stem Cell Donor Registry, with 80,000 potential donors identified. The aim is to identify universal donors, reprogram their cells into induced pluripotent stem (iPS) cells, and create a gene bank for matched tissue transplants. Alsayegh is collaborating with Jesper Tegnér at KAUST to create pacemaker cells using single-cell RNA sequencing. Why it matters: This initiative could revolutionize precision medicine in KSA by providing readily available, matched cells for transplants, reducing the need for patient-specific reprogramming and improving treatment outcomes.
KAUST and Janssen Pharmaceutical (Johnson & Johnson) are collaborating to research and innovate in neglected tropical diseases, focusing on dengue fever. They signed an MoU to establish a dengue fever research program and an infectious disease R&D center at KAUST's National BioPark. The partnership marks Johnson & Johnson's first university collaboration in Saudi Arabia. Why it matters: This collaboration signifies a major step in localizing disease research within Saudi Arabia and leveraging KAUST's AI, genomics, and data simulation expertise to address global health challenges.
The study compares deep learning models trained via transfer learning from ImageNet (TII-models) against those trained solely on medical images (LMI-models) for disease segmentation. Results show that combining outputs from both model types can improve segmentation performance by up to 10% in certain scenarios. A repository of models, code, and over 10,000 medical images is available on GitHub to facilitate further research.
The paper proposes a method for causal inference using satellite image time series to determine the impact of interventions on climate change, focusing on quantifying deforestation due to human causes. The method uses computer vision and deep learning to detect forest tree coverage levels over time and Bayesian structural causal models to estimate counterfactuals. The framework is applied to analyze deforestation levels before and after the hyperinflation event in Brazil in the Amazon rainforest region.
KAUST researchers led by Pascal Saikaly are developing microbial electrochemical technologies (METs) for wastewater treatment and energy recovery. The team combines METs with membrane filtration, creating a hybrid air-biocathode microbial fuel cell-membrane bioreactor (MFC-MBR) for simultaneous wastewater treatment and ultrafiltration. This system uses an electrically conductive ultrafiltration membrane as a biocathode for electricity generation and passive oxygen transfer. Why it matters: This innovation offers a sustainable approach to water reclamation by reducing energy consumption and producing reusable water, which addresses critical water scarcity challenges in the region and globally.
A new paper coauthored by researchers at The University of Melbourne and MBZUAI explores disagreement in human annotation for AI training. The paper treats disagreement as a signal (human label variation or HLV) rather than noise, and proposes new evaluation metrics based on fuzzy set theory. These metrics adapt accuracy and F-score to cases where multiple labels may plausibly apply, aligning model output with the distribution of human judgments. Why it matters: This research addresses a key challenge in NLP by accounting for the inherent ambiguity in human language, potentially leading to more robust and human-aligned AI systems.
A new paper from MBZUAI introduces JEEM, a benchmark dataset for evaluating vision-language models on their understanding of images grounded in four Arabic-speaking societies (Jordan, UAE, Egypt, and Morocco) and their ability to use local dialects. The dataset comprises 2,178 images and 10,890 question-answer pairs reflecting everyday life and culturally specific scenes. Evaluation of several Arabic-capable models (Maya, PALO, Peacock, AIN, AyaV) and GPT-4o revealed that while models can generate fluent language, they struggle with genuine understanding, consistency, and relevance, especially when cultural context is important. Why it matters: This research highlights the challenges of building AI systems that can truly understand and interact with diverse cultures, emphasizing the need for culturally grounded datasets and evaluation metrics.
An MBZUAI team led by Thamar Solorio and Monojit Choudhury received a Google Academic Research Award to study how AI can better understand and respond to human loneliness in digital spaces. The project will examine how loneliness is expressed online, how conversational agents can detect it, and what healthier AI companionship could look like in collaboration with Georgia Tech. The team aims to define digital loneliness and its expression in online conversations with AI. Why it matters: This research addresses a growing global issue by exploring the ethical and psychological implications of AI companionship, potentially leading to safer and more beneficial AI interactions.
MBZUAI researchers have developed a new method called "Byzantine antidote" (Bant) to defend federated learning systems against Byzantine attacks, where malicious nodes intentionally disrupt the training process. Bant uses trust scores and a trial function to dynamically filter out corrupted updates, even when most nodes are compromised. The system can identify poorly labeled data while still training models effectively, addressing both unconscious mistakes and deliberate sabotage. Why it matters: This research enhances the reliability and security of federated learning in sensitive sectors like healthcare and finance, enabling safer collaborative AI development.
MBZUAI researchers developed MedAgentSim, a simulated hospital environment to evaluate AI diagnostic abilities. The simulation uses LLM-powered agents to mimic doctor-patient conversations, providing a dynamic assessment of diagnostic skills. The system includes doctor, patient, and evaluator agents that interact within the simulated hospital, making real-time decisions. Why it matters: This research offers a more realistic evaluation of AI in clinical settings, addressing limitations of current benchmarks and potentially improving AI's use in healthcare.
MBZUAI has partnered with the World Economic Forum to launch a Centre for the Fourth Industrial Revolution (C4IR) in the UAE. This center will focus on AI, energy transition, and cyber resilience, aiming to advance AI excellence and competitiveness in the region. It will convene leaders across sectors to co-design and pilot initiatives supporting AI research, governance, adoption, and innovation. Why it matters: This partnership positions the UAE and MBZUAI as key players in shaping the global AI landscape and addressing pressing economic, social, and human challenges through AI.
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 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.
MBZUAI researchers introduced CausalVerse, a new benchmark for causal representation learning (CRL) presented at NeurIPS 2025. CausalVerse combines high-fidelity visual complexity with access to underlying causal variables and graphs, featuring 200,000 images and 300 million video frames across 24 sub-scenes in four domains. It aims to provide a realistic and precise testbed to evaluate whether CRL methods can truly learn the right causes. Why it matters: By bridging the gap between toy datasets and real-world data, CausalVerse can drive advances in AI systems capable of understanding causality in complex scenarios.