The ability to simulate human privacy decisions has significant implications for aligning autonomous agents with individual intent and conducting cost-effective, large-scale privacy-centric user studies. Prior approaches prompt Large Language Models (LLMs) with natural language user statements, data-sharing histories, or demographic attributes to simulate privacy decisions. These approaches, however, fail to balance individual-level accuracy, prompt usability, token efficiency, and population-level representation. We present Narriva, an approach that generates text-based synthetic privacy personas to address these shortcomings. Narriva grounds persona generation in prior user privacy decisions, such as those from large-scale survey datasets, rather than purely relying on demographic stereotypes. It compresses this data into concise, human-readable summaries structured by established privacy theories. Through benchmarking across five diverse datasets, we analyze the characteristics of Narriva's synthetic personas in modeling both individual and population-level privacy preferences. We find that grounding personas in past privacy behaviors achieves up to 88% predictive accuracy (significantly outperforming a non-personalized LLM baseline), and yields an 80-95% reduction in prompt tokens compared to in-context learning with raw examples. Finally, we demonstrate that personas synthesized from a single survey can reproduce the aggregate privacy behaviors and statistical distributions (TVComplement up to 0.85) of entirely different studies.

翻译：模拟人类隐私决策的能力对于使自主智能体与个体意图对齐，以及开展经济高效的大规模隐私用户研究具有重要意义。现有方法通过向大语言模型（LLMs）输入自然语言用户陈述、数据共享历史或人口统计属性来模拟隐私决策。然而，这些方法在平衡个体级准确性、提示可用性、词元效率与群体级代表性方面存在不足。本文提出Narriva方法，通过生成基于文本的合成隐私画像来解决上述缺陷。Narriva并非单纯依赖人口统计刻板印象，而是将画像生成建立在先前的用户隐私决策（如大规模调查数据集中的记录）之上，并将这些数据压缩为由成熟隐私理论构建的简洁可读摘要。通过在五个不同数据集上进行基准测试，我们分析了Narriva合成画像在建模个体级与群体级隐私偏好时的特征。研究发现，将画像建立在先前隐私行为基础上可实现高达88%的预测准确率（显著优于非个性化LLM基线），且与使用原始样本的上下文学习相比，可减少80-95%的提示词元。最后，我们证明从单一调查中合成的画像能够复现完全不同研究中的总体隐私行为与统计分布（TVComplement最高达0.85）。