CRMar 20

Text-Based Personas for Simulating User Privacy Decisions

arXiv:2603.1979198.42 citationsh-index: 23
AI Analysis

This addresses the need for cost-effective, large-scale privacy-centric user studies and aligning autonomous agents with individual intent, representing a novel method for a known bottleneck.

The researchers tackled the problem of simulating human privacy decisions by developing Narriva, which generates text-based synthetic privacy personas grounded in past user privacy behaviors rather than demographic stereotypes, achieving up to 88% predictive accuracy and 80-95% reduction in prompt tokens compared to baselines.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes