---
title: "AISPA：面向用户的大语言模型系统提示词审计框架"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.28617v1"
permalink: "https://feed.astralor.com/items/itm_c810c8dbd437114452a52e18"
published: "2026-07-30T17:58:58.000Z"
score: 76
channel: "ai"
tags: ["AISPA","AI审计","AI治理","大语言模型","系统提示词"]
---

# AISPA：面向用户的大语言模型系统提示词审计框架

## AI 点评

> 这篇论文的价值在于它把系统提示词从幕后拉到了聚光灯下，用数据证明商业AI的透明度缺口真实且严重。对开发者来说，AISPA提供了一套可以直接对照自查的清单；对监管者来说，这是推动提示词公开与标准化的重要依据。建议关注AI治理与产品安全的人细读。

## 速览

系统提示词决定了大模型应用的行为，但商业产品极少公开，造成信任与问责缺口。本文提出AISPA框架，从八个维度对系统提示词进行用户视角审计，并分析了88款商业AI产品中的3249条指令。结果显示：保护性指令普遍存在但深度不足，仅24%产品覆盖全部八维度；同时约40%产品包含损害用户利益的指令，保护与问题指令常共存。研究呼吁提升系统提示词的透明度、标准化与独立监管。

## 关键点

- 提出AISPA框架，从八个用户相关维度系统审计系统提示词
- 覆盖88款商业AI产品中的3249条提示词指令，分类为保护性或问题性
- 发现仅24%产品覆盖全部保护维度，约40%产品包含损害用户利益的指令

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_c810c8dbd437114452a52e18