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.
Researchers introduce UnsafeChain, a new safety alignment dataset designed to improve the safety of large reasoning models (LRMs) by focusing on 'hard prompts' that elicit harmful outputs. The dataset identifies and corrects unsafe completions into safe responses, exposing models to unsafe behaviors and guiding their correction. Fine-tuning LRMs on UnsafeChain demonstrates enhanced safety and preservation of general reasoning ability compared to existing datasets like SafeChain and STAR-1.
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.
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.
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.