让AI代理在社交中智能权衡隐私保护与必要披露。
AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
- 设计能感知社交情境的隐私自披露机制
- 用户研究验证其在多种关系中有效平衡隐私与目标达成
- 适合需人机社交互动的隐私敏感场景
基于大语言模型的AI代理正广泛用于代表用户完成各类任务，尤其在对话界面中。然而，社交场景中隐私泄露风险凸显——既需保护敏感信息，又常需披露部分私密内容以达成目标。现有研究多通过限制访问来保护隐私，但忽视了社交情境下的披露需求。本文首先开展预研，调查用户在不同社交关系与任务中的认知；随后提出一种具备隐私意识的自披露AI代理系统。用户研究表明，该系统能在多样动态社交交互中实现策略性隐私保护，首次将此能力应用于复杂社交场景。
原文摘要 · Abstract (English)
Large language model (LLM)-based AI delegates are increasingly utilized to act on behalf of users, assisting them with a wide range of tasks through conversational interfaces. Despite their advantages, concerns arise regarding the potential risk of privacy leaks, particularly in scenarios involving social interactions. While existing research has focused on protecting privacy by limiting the access of AI delegates to sensitive user information, many social scenarios require disclosing private details to achieve desired social goals, necessitating a balance between privacy protection and disclosure. To address this challenge, we first conduct a pilot study to investigate user perceptions of AI delegates across various social relations and task scenarios, and then propose a novel AI delegate system that enables privacy-conscious self-disclosure. Our user study demonstrates that the proposed AI delegate strategically protects privacy, pioneering its use in diverse and dynamic social interactions.
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。