PrivacyReasoner: LLM能否模拟出类似人类的隐私思维？
PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?
AI总结：
本文提出PrivacyReasoner，通过构建基于三个核心理念的代理架构，模拟人类隐私思维，评估结果显示其在预测个人隐私关切和跨领域泛化方面优于基线模型。
摘要：
先前基于LLM的隐私研究集中于合成场景中的规范判断，而非人们如何思考特定数据实践并形成观点。我们通过设计PrivacyReasoner，一种基于三个关键理念的代理架构来填补这一空白：(1) LLM能够检测自然语言中的微妙隐私线索并扮演人类特征；(2) 用户的“隐私思维”可以从其现实生活中的在线评论历史中重建，提炼出经验、个性和文化取向；(3) 上下文过滤器可以根据场景中的上下文动态激活相关的隐私信念。我们在Hacker News的现实隐私讨论中评估PrivacyReasoner，使用一个基于已建立的隐私关切分类法校准的LLM-as-a-Judge评估器来量化推理的忠实度。PrivacyReasoner在预测个体隐私关切方面显著优于基线模型，并且在AI、电子商务和医疗等不同领域中实现了跨领域泛化。
英文摘要：
Prior work on LLM-based privacy focuses on norm judgment over synthetic vignettes, rather than how people think about a specific data practice and formulate their opinions. We address this gap by designing PrivacyReasoner, an agent architecture grounded in three key ideas: (1) LLMs can detect subtle privacy cues in natural language and role-play human characteristics; (2) a user's ``privacy mind'' can be reconstructed from their real-world online comment history, distilling experiences, personality, and cultural orientations; and (3) a contextual filter can dynamically activate relevant privacy beliefs based on the contexts in a scenario. We evaluate PrivacyReasoner on real-world privacy discussions from Hacker News, using an LLM-as-a-Judge evaluator calibrated against an established privacy concern taxonomy to quantify reasoning faithfulness. PrivacyReasoner significantly outperforms baselines in predicting individual privacy concerns and generalizes across different domains, such as AI, e-commerce, and healthcare.
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。
