@inproceedings{chen-etal-2025-personatwin,
    title = "{P}ersona{T}win: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins",
    author = "Chen, Sihan  and
      Lalor, John P.  and
      Yang, Yi  and
      Abbasi, Ahmed",
    editor = "Dhole, Kaustubh  and
      Clinciu, Miruna",
    booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
    month = jul,
    year = "2025",
    address = "Vienna, Austria and virtual meeting",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.gem-1.66/",
    pages = "774--788",
    ISBN = "979-8-89176-261-9",
    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 $\texttt{PersonaTwin}$, 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 $\texttt{PersonaTwin}$ 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."
}