Skip to main content
This is a research prototype. The data and analyses are preliminary and not yet validated — we'd welcome your .

Physical Health

SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions

Zhang et al. (2023)

Category
Risk Domain

AI systems that inadvertently generate or spread incorrect or deceptive information, which can lead to inaccurate beliefs in users and undermine their autonomy. Humans that make decisions based on false beliefs can experience physical, emotional or material harms

"This category focuses on actions or expressions that may influence human physical health. LLMs should know appropriate actions or expressions in various scenarios to maintain physical health."(p. 3)

Other risks from Zhang et al. (2023) (6)