PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins
This work addresses the need for realistic and nuanced user simulations in personalized digital modeling, particularly in healthcare, though it appears incremental as an enhancement to existing LLM-based approaches.
The authors tackled the problem of LLMs failing to capture individual user nuances by introducing PersonaTwin, a multi-tier prompt conditioning framework for generating personalized digital twins, which achieved simulation fidelity on par with oracle settings and enabled downstream models to approximate individual-based training in prediction and fairness metrics.
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.