Röttger P, Pernisi F, Vidgen B, Hovy D. SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety. AAAI [Internet]. 2025Apr.11 [cited 2026May1];39(26):27617-2. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34975