The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
核心要点速览
Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。