Language model (LM) agents that act on users' behalf for personal tasks can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee the privacy implications of the LM agents. By conducting a task-based survey (N=300), we investigate how people react to and assess the response generated by LM agents for asynchronous interpersonal communication tasks, compared with a response they wrote. We found that people may favor the agent response with more privacy leakage over the response they drafted or consider both good, leading to an increased harmful disclosure from 15.7% to 55.0%. We further uncovered distinct patterns of privacy behaviors, attitudes, and preferences, and the nuanced interactions between privacy considerations and other factors. Our findings shed light on designing agentic systems that enable privacy-preserving interactions and achieve bidirectional alignment on privacy preferences to help users calibrate trust.

翻译：语言模型智能体代表用户处理个人任务时能提升工作效率，但也容易引发非预期的隐私泄露风险。本研究首次探讨了人类监督语言模型智能体隐私影响的能力。通过一项基于任务的问卷调查（N=300），我们比较了人们在异步人际沟通任务中，对语言模型智能体生成回复与自己撰写回复的反应与评估。研究发现：相较于自己撰写的回复，人们可能更青睐包含更多隐私泄露风险的智能体回复，或认为两者皆可接受，导致有害信息披露率从15.7%上升至55.0%。我们进一步揭示了隐私行为、态度与偏好的差异化模式，以及隐私考量与其他因素间的微妙相互作用。这些发现为设计具有隐私保护功能的智能体系统提供了启示，通过实现隐私偏好的双向对齐，帮助用户校准信任关系。