Adel Bibi, a KAUST alumnus and researcher at the University of Oxford, presented his research on AI safety, covering robustness, alignment, and fairness of LLMs. The research addresses challenges in AI systems, alignment issues, and fairness across languages in common tokenizers. Bibi's work includes instruction prefix tuning and its theoretical limitations towards alignment. Why it matters: This research from a leading researcher highlights the importance of addressing safety concerns in LLMs, particularly regarding alignment and fairness in the Arabic language.
The paper introduces SalamahBench, a new benchmark for evaluating the safety of Arabic Language Models (ALMs). The benchmark comprises 8,170 prompts across 12 categories aligned with the MLCommons Safety Hazard Taxonomy. Five state-of-the-art ALMs, including Fanar 1 and 2, ALLaM 2, Falcon H1R, and Jais 2, were evaluated using the benchmark. Why it matters: The benchmark enables standardized, category-aware safety evaluation, highlighting the necessity of specialized safeguard mechanisms for robust harm mitigation in ALMs.
Mykel Kochenderfer from Stanford University gave a talk on building robust decision-making systems for autonomous systems, highlighting the challenges of balancing safety and efficiency in uncertain environments. The talk addressed computational tractability and establishing trust in these systems. Kochenderfer outlined methodologies and research applications for building safer systems, drawing from his work on air traffic control, unmanned aircraft, and automated driving. Why it matters: The development of safe and reliable autonomous systems is crucial for various applications in the region, and insights from experts like Kochenderfer can guide research and development efforts at institutions like MBZUAI.