Simulating Persuasive Dialogues on Meat Reduction with Generative Agents

Researchers from the University of Mannheim and the University of Basel presented work in progress at the First Workshop on Integrating NLP and Psychology to Study Social Interactions (NLPSI) @ICWSMS '25 showing that large language model-based generative agents can simulate persuasive dialogues on meat reduction, producing outcomes consistent with the Theory of Planned Behavior and valid against prior human participant data. The study, led by Georg Ahnert, Elena Wurth, Markus Strohmaier, and Jutta Mata, suggests generative agent-based models could identify novel communication strategies tailored to specific participant groups before costly human testing.

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.- Anthology ID: - 2025.nlpsi-1.1 - Volume: Proceedings of the First Workshop on Integrating NLP and Psychology to Study Social Interactions NLPSI @ICWSM ’25 /volumes/2025.nlpsi-1/ - Month: - June - Year: - 2025 - Address: - Copenhagen, Denmark - Editors: Aswathy Velutharambath /people/aswathy-velutharambath/unverified/ , Sofie Labat /people/sofie-labat/ , Neele Falk /people/neele-falk/ , Flor Miriam Plaza-del-Arco /people/flor-miriam-plaza-del-arco/ , Roman Klinger /people/roman-klinger/ , Véronique Hoste /people/veronique-hoste/unverified/ - Venues: NLPSI /venues/nlpsi/ | WS /venues/ws/ - SIG: - Publisher: - Association for the Advancement of Artificial Intelligence www.aaai.org - Note: - Pages: - 1–10 - Language: - URL: https://aclanthology.org/2025.nlpsi-1.1/ https://aclanthology.org/2025.nlpsi-1.1/ - DOI: 10.36190/2025.30 https://doi.org/10.36190/2025.30 - Cite ACL : - Georg Ahnert, Elena Wurth, Markus Strohmaier, and Jutta Mata. 2025. Simulating Persuasive Dialogues on Meat Reduction with Generative Agents https://aclanthology.org/2025.nlpsi-1.1/ . In Proceedings of the First Workshop on Integrating NLP and Psychology to Study Social Interactions NLPSI @ICWSM ’25 , pages 1–10, Copenhagen, Denmark. Association for the Advancement of Artificial Intelligence www.aaai.org . - Cite Informal : Simulating Persuasive Dialogues on Meat Reduction with Generative Agents https://aclanthology.org/2025.nlpsi-1.1/ Ahnert et al., NLPSI 2025 - PDF: https://aclanthology.org/2025.nlpsi-1.1.pdf https://aclanthology.org/2025.nlpsi-1.1.pdf