Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
校准的预测下界:在大语言模型中时间到不安全采样的预测下界
机构 * Department of Computer Science, Technion IIT(计算机科学系) ; Department of Statistics, University of Oxford(统计系) ; Department of Electrical and Computer Engineering, Technion IIT(电气与计算机工程系)
AI总结 本文提出了一种基于生存分析的校准技术,用于构建大语言模型中时间到不安全采样的预测下界,以提高安全风险评估的可靠性。