用小模型让用户自主删敏感信息，保护聊天机器人隐私。
Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots
- 用浏览器插件帮用户识别并清除提示中的个人隐私信息
- 12人测试显示隐私担忧降低，体验接近GPT-4o水平
- 适合关注隐私、想掌控数据的普通用户
基于大模型的对话代理导致过多可识别或敏感信息泄露。现有技术因缺乏用户参与，难以提供可感知的控制或适配个人隐私-效用权衡偏好。为此，我们设计、构建并评估了Rescriber——一个浏览器扩展，通过帮助用户检测和清理提示中的个人信息，实现用户主导的数据最小化。12人研究显示，Rescriber有效减少非必要披露，缓解隐私担忧；基于Llama3-8B的系统在用户主观感知上与GPT-4o相当。检测与清洗的全面性和一致性是影响用户信任和感知保护的关键因素。研究证实，由小型模型驱动、面向用户、本地运行的隐私控制可行，为应对AI隐私与信任挑战提供了有前景的方案。
原文摘要 · Abstract (English)
The proliferation of LLM-based conversational agents has resulted in excessive disclosure of identifiable or sensitive information. However, existing technologies fail to offer perceptible control or account for users' personal preferences about privacy-utility tradeoffs due to the lack of user involvement. To bridge this gap, we designed, built, and evaluated Rescriber, a browser extension that supports user-led data minimization in LLM-based conversational agents by helping users detect and sanitize personal information in their prompts. Our studies (N=12) showed that Rescriber helped users reduce unnecessary disclosure and addressed their privacy concerns. Users' subjective perceptions of the system powered by Llama3-8B were on par with that by GPT-4o. The comprehensiveness and consistency of the detection and sanitization emerge as essential factors that affect users' trust and perceived protection. Our findings confirm the viability of smaller-LLM-powered, user-facing, on-device privacy controls, presenting a promising approach to address the privacy and trust challenges of AI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。