PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins

TL;DR

PersonaTwin is a multi-tier prompt framework that creates personalized digital twins from demographic, behavioral, and psychometric data, improving simulation fidelity and fairness in user modeling with LLMs.

Contribution

It introduces PersonaTwin, a novel multi-tier prompt conditioning framework that enhances the realism and fairness of personalized digital twins using comprehensive user data.

Findings

Achieves simulation fidelity comparable to oracle settings.

Downstream models trained on persona-twins match individual-based models in prediction.

Ensures generated responses are accurate and unbiased.

Abstract

While large language models (LLMs) afford new possibilities for user modeling and approximation of human behaviors, they often fail to capture the multidimensional nuances of individual users. In this work, we introduce PersonaTwin, a multi-tier prompt conditioning framework that builds adaptive digital twins by integrating demographic, behavioral, and psychometric data. Using a comprehensive data set in the healthcare context of more than 8,500 individuals, we systematically benchmark PersonaTwin against standard LLM outputs, and our rigorous evaluation unites state-of-the-art text similarity metrics with dedicated demographic parity assessments, ensuring that generated responses remain accurate and unbiased. Experimental results show that our framework produces simulation fidelity on par with oracle settings. Moreover, downstream models trained on persona-twins approximate models trained on individuals in terms of prediction and fairness metrics across both GPT-4o-based and Llama-based models. Together, these findings underscore the potential for LLM digital twin-based approaches in producing realistic and emotionally nuanced user simulations, offering a powerful tool for personalized digital user modeling and behavior analysis.