1
AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety
AI伴侣安全性如何评估?这个新基准让大模型自己当裁判,专治LLM越狱与不当行为。
arXiv:2606.04867v1 Announce Type: new Abstract: As AI companion platforms such as Replika and Character.AI rapidly grow, concerns about unsafe human-A…