@inproceedings{liu-etal-2025-mosaic,
    title = "{MOSAIC}: Modeling Social {AI} for Content Dissemination and Regulation in Multi-Agent Simulations",
    author = "Liu, Genglin  and
      Le, Vivian T.  and
      Rahman, Salman  and
      Kreiss, Elisa  and
      Ghassemi, Marzyeh  and
      Gabriel, Saadia",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.325/",
    pages = "6401--6428",
    ISBN = "979-8-89176-332-6",
    abstract = "We present a novel, open-source social network simulation framework, MOSAIC, where generative language agents predict user behaviors such as liking, sharing, and flagging content. This simulation combines LLM agents with a directed social graph to analyze emergent deception behaviors and gain a better understanding of how users determine the veracity of online social content. By constructing user representations from diverse fine-grained personas, our system enables multi-agent simulations that model content dissemination and engagement dynamics at scale. Within this framework, we evaluate three different content moderation strategies with simulated misinformation dissemination, and we find that they not only mitigate the spread of non-factual content but also increase user engagement. In addition, we analyze the trajectories of popular content in our simulations, and explore whether simulation agents' articulated reasoning for their social interactions truly aligns with their collective engagement patterns."
}