Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications 事件

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications arXiv:2605.24883v1 Announce Type: new Abstract: The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effective, these approaches face challenges, as they depend heavily on e