@inproceedings{ahnert-etal-2025-simulating,
    title = "Simulating Persuasive Dialogues on Meat Reduction with Generative Agents",
    author = "Ahnert, Georg  and
      Wurth, Elena  and
      Strohmaier, Markus  and
      Mata, Jutta",
    editor = "Velutharambath, Aswathy  and
      Labat, Sofie  and
      Falk, Neele  and
      Plaza-del-Arco, Flor Miriam  and
      Klinger, Roman  and
      Hoste, V{\'e}ronique",
    booktitle = "Proceedings of the First Workshop on Integrating {NLP} and Psychology to Study Social Interactions ({NLPSI}) @{ICWSM} `25",
    month = jun,
    year = "2025",
    address = "Copenhagen, Denmark",
    publisher = "Association for the Advancement of Artificial Intelligence (www.aaai.org)",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2025.nlpsi-1.1/",
    pages = "1--10",
    abstract = "Meat reduction benefits human and planetary health, but social norms keep meat central in shared meals.To date, the development of {\_}communication strategies that promote meat reduction while minimizing social costs{\_} has required the costly involvement of human participants at each stage of the process.We present work in progress on simulating multi-round dialogues on meat reduction between {\_}Generative Agents{\_} based on large language models (LLMs). We measure our main outcome using established psychological questionnaires based on the {\_}Theory of Planned Behavior{\_} and additionally investigate {\_}Social Costs{\_}.We find evidence that our preliminary simulations produce outcomes that are (i) consistent with theoretical expectations; and (ii) valid when compared to data from previous studies with human participants. Generative agent-based models are a promising tool for identifying novel communication strategies on meat reduction{---}tailored to highly specific participant groups{---}to then be tested in subsequent studies with human participants."
}