The paper introduces ORCA, a new public benchmark for evaluating Arabic language understanding. ORCA covers diverse Arabic varieties and includes 60 datasets across seven NLU task clusters. The benchmark was used to compare 18 multilingual and Arabic language models and includes a public leaderboard with a unified evaluation metric. Why it matters: ORCA addresses the lack of a comprehensive Arabic benchmark, enabling better progress measurement for Arabic and multilingual language models.
Professor Omar Knio has been appointed as the new dean of the Computer, Electrical and Mathematical Sciences and Engineering Division at KAUST, following the departure of Professor Gianluca Setti. Knio previously served as the division's interim dean and has held multiple leadership positions at KAUST since 2012. He aims to lead key initiatives central to KAUST's strategic mission while also serving as vice president of academic affairs. Why it matters: Knio's appointment signals KAUST's continued investment in computational sciences and engineering, crucial for advancements in AI and technology within Saudi Arabia.