Muhammad Arslan Manzoor became MBZUAI's first NLP Ph.D. graduate, focusing his research on media bias under Professor Preslav Nakov. His thesis, 'MGM,' explored using audience overlap graphs to predict the factuality and bias of news media, an approach that differs from traditional textual analysis. Manzoor's work aims to improve the efficiency of media profiling in real-time by leveraging relationships captured in media graphs. Why it matters: This research offers innovative methods for identifying bias in news, which is crucial for promoting informed social discourse and combating disinformation in the region.
MBZUAI student Zain Muhammad Mujahid is researching methods to detect media bias using NLP and LLMs. His approach profiles bias across media outlets using LLMs like ChatGPT to predict bias based on 16 identifiers. The research aims to develop a tool that instantly provides a bias profile for a given media URL. Why it matters: This research has the potential to combat misinformation and enhance media literacy in the region by providing tools to identify biased reporting, and it is expanding to Arabic and other languages.
MBZUAI will graduate its first three Ph.D. students on June 6, 2024. Numan Saeed's research focused on using AI and big data to diagnose head and neck cancers using PET and CT scans, aided by NLP to interpret doctors' notes. The graduates will remain in the UAE to contribute to the country's growing AI sector. Why it matters: This milestone highlights the growing AI talent pool in the UAE and the potential for AI research at MBZUAI to address critical healthcare challenges.
MBZUAI researcher Karima Kadaoui is using AI to assist disadvantaged communities and languages, with a focus on democratizing NLP tasks for Arabic dialects. Her master's thesis focused on impaired speech recognition, converting disfluencies of individuals with speech disabilities into clear speech. She emphasizes the importance of diversity and inclusion in AI to avoid bias and ensure systems reflect the user distribution. Why it matters: This highlights MBZUAI's commitment to gender equity in STEM and the development of AI solutions tailored to the nuances of the Arabic language.
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.