系统提示是开发人员配置的指令，用于管理人工智能应用程序中基础模型的行为。它们在整个商业人工智能产品中使用,，但很少向公众或监管机构披露,，从而在人工智能系统的广泛部署中造成严重的信任和责任差距。在本文,中，我们介绍了人工智能系统提示保证(AISPA),一个以用户为中心的框架，用于系统地审核人工智能系统中的系统提示。 AISPA 检查系统提示的特定部分，并根据对用户重要的八个维度对其进行评估。然后，我们使用此框架审查 88 个商业 AI 产品, 中系统提示中的 3,249 条指令，将每条指令分类为保护 ( 的用户) 或有问题的指令。我们的审计揭示了四个核心发现。首先, 系统提示设计在不同产品和开发人员, 之间存在很大差异，一些组织平均每个产品有超过 60 条保护指令，而其他组织平均不到 5 条。其次, 保护指令被广泛采用，但范围较浅: 98.9% 的产品至少包含 1,，但只有 24% 涵盖 AISPA 分类法的所有八个维度。第三, 系统提示已稳步增长，并且对用户的保护越来越多, 这表明用户保护正在成为商业提示设计中更加明显的关注点。第四, 尽管取得了这一进展, 有问题的指令仍然普遍存在: 大约 40% 的产品至少包含一条不利于用户利益的指令, 并且保护性指令和有问题的指令经常在同一提示中共存。我们的研究结果强调需要提高透明度,标准化,以及对商业人工智能产品中的系统提示进行独立监督。
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 framework for systematically auditing system prompts in AI systems. AISPA examines specific parts of a system prompt and evaluates them along eight dimensions that matter to users. We then use this framework to review 3,249 instructions from system prompts in 88 commercial AI products, classifying each instruction as either protective (of users) or problematic. Our audit surfaces four core findings. First, system prompt design varies substantially across products and developers, with some organizations averaging over 60 protective instructions per product while others average fewer than 5. Second, protective instructions are widely adopted but shallow in scope: 98.9% of products contain at least one, yet only 24% cover all eight dimensions of the AISPA taxonomy. Third, system prompts have grown steadily longer and more protective of users, suggesting that user protection is becoming a more visible concern in commercial prompt design. Fourth, despite this progress, problematic instructions remain pervasive: roughly 40% of products contain at least one instruction that works against user interests, and protective and problematic instructions frequently coexist within the same prompt. Our findings highlight the need for greater transparency, standardization, and independent oversight for system prompts in commercial AI products.
科目: 人工智能 (cs.AI); 计算与语言 (cs.CL); 计算机与社会 (cs.CY); 人机交互 (cs.HC)
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)