#artificial intelligence
Dec 2025
The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior
The stability of safety refusal decisions across random seeds and temperature settings is investigated by investigating the stability of safety refusal decisions across random seeds and temperature settings to demonstrate that single-shot safety evaluations are insufficient for reliable safety assessment and that evaluation protocols must account for stochastic variation in model behavior.
E. Larsen
· arXiv.org · 4 citations