@inproceedings{bui-etal-2025-mixture,
    title = "Mixture-of-Personas Language Models for Population Simulation",
    author = "Bui, Ngoc  and
      Nguyen, Hieu Trung  and
      Kumar, Shantanu  and
      Theodore, Julian  and
      Qiu, Weikang  and
      Nguyen, Viet Anh  and
      Ying, Rex",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.1271/",
    pages = "24761--24778",
    ISBN = "979-8-89176-256-5",
    abstract = "Advances in Large Language Models (LLMs) paved the way for their emerging applications in various domains, such as human behavior simulations, where LLMs could augment human-generated data in social science research and machine learning model training. However, pretrained LLMs often fail to capture the behavioral diversity of target populations due to the inherent variability across individuals and groups. To address this, we propose \textit{Mixture of Personas} (MoP), a \textit{probabilistic} prompting method that aligns LLM responses with the target population. MoP is a contextual mixture model, where each component is an LM agent characterized by a persona and an exemplar that represents the behaviors of subpopulation. The persona and the exemplar are randomly chosen according to the learned mixing weights to elicit diverse LLM responses during simulation. MoP is flexible, does not require model fine-tuning, and is transferable between base models. Experiments for synthetic data generation show that MoP outperforms competing methods in alignment and diversity metrics."
}