@inproceedings{baltaji-etal-2024-conformity,
    title = "Conformity, Confabulation, and Impersonation: Persona Inconstancy in Multi-Agent {LLM} Collaboration",
    author = "Baltaji, Razan  and
      Hemmatian, Babak  and
      Varshney, Lav",
    editor = "Prabhakaran, Vinodkumar  and
      Dev, Sunipa  and
      Benotti, Luciana  and
      Hershcovich, Daniel  and
      Cabello, Laura  and
      Cao, Yong  and
      Adebara, Ife  and
      Zhou, Li",
    booktitle = "Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.c3nlp-1.2/",
    doi = "10.18653/v1/2024.c3nlp-1.2",
    pages = "17--31",
    abstract = "This study explores the sources of instability in maintaining cultural personas and opinions within multi-agent LLM systems. Drawing on simulations of inter-cultural collaboration and debate, we analyze agents' pre- and post-discussion private responses alongside chat transcripts to assess the stability of cultural personas and the impact of opinion diversity on group outcomes. Our findings suggest that multi-agent discussions can encourage collective decisions that reflect diverse perspectives, yet this benefit is tempered by the agents' susceptibility to conformity due to perceived peer pressure and challenges in maintaining consistent personas and opinions. Counterintuitively, instructions that encourage debate in support of one{'}s opinions increase the rate of instability. Without addressing the factors we identify, the full potential of multi-agent frameworks for producing more culturally diverse AI outputs will remain untapped."
}