1
Online Safety Monitoring for LLMs
论文提出在线安全监控LLM的新方法，引入假设检验框架，为模型部署提供实时风险检测思路。
arXiv:2607.02510v1 Announce Type: new Abstract: Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitor…
2
Computational Safety for Generative AI: A Hypothesis Testing Perspective
用假设检验理论重新审视生成式AI安全问题，为模型风险量化提供严谨数学框架。
arXiv:2502.12445v2 Announce Type: replace Abstract: AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of front…
3
E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing
用序列假设检验提升AI Agent验证器可靠性，新方法E-valuator值得关注。
arXiv:2512.03109v2 Announce Type: replace-cross Abstract: Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in …
4
Statistical Unlearning of Distributions: A Hypothesis Testing Approach
用假设检验框架实现分布级统计遗忘，为机器学习遗忘机制提供新理论视角。
arXiv:2605.16645v1 Announce Type: cross Abstract: Machine learning systems increasingly face requirements to forget not only individual data points, b…