AISPA：面向用户的 LLM 系统提示审计框架
原标题：AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
AI 摘要
AISPA 框架提出了一种以用户为中心的系统提示审计方法，用于评估 AI 应用中的系统提示。研究团队对 88 个商业 AI 产品中的 3,249 条系统提示指令进行了审查，发现系统提示设计差异显著，保护性指令虽广泛采用但覆盖范围有限，且约 40% 的产品包含不利于用户的指令。该研究强调了商业 AI 产品中系统提示透明度和标准化的重要性。
正文节选
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications Abstract System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regulators, creating a serious trust and accountability gap in the wide deployment of AI systems. In this paper, we introduce Artificial Intelligence System Prompt Assurance (AISPA), a user-centric