Skip to content

Critics Can Be Harmful: On the Safety of LLM-Guided AutoML Search

The Critic Can Hurt: On the Safety of Critics in LLM-Guided AutoML Search

arXiv: 其他 AI 安全论文· arXiv:2611.19037· Gaoyuan Du, Xiaoyang Liu, Rex Zhou, Dengdu Jiang, Rong Fu, Meng Ding, Defu CaoAmazon; University of Massachusetts Boston; University of Southern CaliforniaIndexed by this site · 2 days ago· Originally publishedEvaluation· Its place in the scan record →

Translation in progress — untranslated text is omitted.

Read originalarxiv.org