This paper introduces a predictive analysis of Arabic court decisions, utilizing 10,813 real commercial court cases. The study evaluates LLaMA-7b, JAIS-13b, and GPT3.5-turbo models under zero-shot, one-shot, and fine-tuned training paradigms, also experimenting with summarization and translation. GPT-3.5 models significantly outperformed others, exceeding JAIS model performance by 50%, while also demonstrating the unreliability of most automated metrics. Why it matters: This research bridges computational linguistics and Arabic legal analytics, offering insights for enhancing judicial processes and legal strategies in the Arabic-speaking world.
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 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.
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 have developed "Culturally Yours," a reading assistant that highlights and explains culturally-specific items on webpages to help users understand unfamiliar terms. The tool addresses the "cold-start problem" by asking users for demographic information to personalize the identification of potentially unfamiliar cultural references. It was presented at the 31st International Conference on Computational Linguistics in Abu Dhabi. Why it matters: This tool can help bridge linguistic and cultural gaps, particularly for underrepresented languages and cultures, and aid businesses in reaching diverse audiences.
The 31st International Conference on Computational Linguistics (COLING 2025) will be held in Abu Dhabi in January 2025, hosted by Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). COLING is a major biennial NLP and AI conference that brings together leaders from research centers, academia, and industry. The conference will feature keynote talks, presentations, workshops, and tutorials, with 1,500 expected participants. Why it matters: Hosting COLING underscores the UAE's growing role in AI and NLP research and provides a platform to address regional linguistic challenges and advance AI technologies.
MBZUAI researchers have expanded LLM safety research to Chinese, presenting their work at the 62nd Annual Meeting of the Association for Computational Linguistics in Bangkok. They developed an open-source Chinese dataset of 3,000 prompts translated and localized from the English "Do-Not-Answer" dataset. The dataset includes a "region-specific sensitivity" category to address unique safety risks for Chinese speakers, evaluating if models are over-sensitive in identifying innocuous questions as harmful. Why it matters: This research addresses a critical gap in LLM safety evaluation, ensuring that language models are both safe and effective for diverse linguistic and cultural contexts, particularly in regions with unique sensitivities.
MBZUAI adjunct professor Iryna Gurevych was appointed to the German National Academy of Sciences Leopoldina and received the “Social Impact Award” at the 18th Conference of the European Chapter of the Association for Computational Linguistics. The Social Impact Award recognized her study on sociodemographic prompting, a technique that steers prompt-based models towards answers reflecting specific sociodemographic profiles. Gurevych was also named one of the 15 most important women in AI in Germany by Manager Magazin for her work building an AI assistant with Amazon. Why it matters: Recognizing experts at MBZUAI raises the visibility of the university and its contributions to cutting-edge NLP research, particularly in areas like ethical and responsible AI development.