让大模型模拟人类隐私思维，能更准确预测真实用户对数据行为的担忧。
PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?
- 用大模型分析自然语言中的隐私线索，角色扮演人类心理特征。
- 基于真实网络评论重建用户隐私观念，涵盖经历、性格与文化背景。
- 根据场景动态激活相关隐私信念，跨领域表现优于现有方法。
现有基于大模型的隐私研究多聚焦于合成情景下的规范判断，缺乏对人们如何思考具体数据实践并形成观点的理解。为此，我们提出PrivacyReasoner，一种基于三个核心思想的智能体架构：（1）大模型可识别自然语言中的细微隐私线索，并模拟人类特征；（2）通过分析用户的现实网络评论历史，重构其“隐私心智”，提取经验、人格与文化取向；（3）设计上下文过滤器，在特定场景中动态激活相关隐私信念。我们在Hacker News的真实隐私讨论上评估了PrivacyReasoner，采用经权威隐私关切分类体系校准的大模型作为评判者，量化推理一致性。结果表明，PrivacyReasoner在预测个体隐私关切方面显著优于基线模型，并在人工智能、电商、医疗等不同领域具有良好泛化能力。
原文摘要 · Abstract (English)
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.
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。