Rescriber：基于小语言模型（Smaller-LLM）的用户主导型数据最小化方法，用于基于大语言模型的聊天机器人
Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots
AI总结：
针对LLM聊天机器人中用户敏感信息过度披露且现有技术缺乏用户参与的问题，本文设计浏览器扩展Rescriber，通过小语言模型帮助用户检测清理提示中的个人信息，实现用户主导的数据最小化，研究表明其能减少不必要披露、缓解隐私担忧，且小模型驱动的系统感知效果与大模型相当。
摘要：
基于大语言模型（LLM）的对话智能体的普及导致可识别或敏感信息的过度披露。然而，由于缺乏用户参与，现有技术无法提供可感知的控制，也无法考虑用户对隐私-效用权衡的个人偏好。为了弥合这一差距，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，支持基于LLM的对话智能体中用户主导的数据最小化。我们的研究（N=12）表明，Rescriber帮助用户减少了不必要的披露，解决了他们的隐私担忧。用户对由Llama3-8B驱动的系统的主观感知与由GPT-4o驱动的系统相当。检测和清理的全面性和一致性成为影响用户信任和感知保护的关键因素。我们的研究结果证实了由小语言模型驱动、面向用户的设备端隐私控制的可行性，为解决人工智能的隐私和信任挑战提供了一种有前景的方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
