EUVIMEDEUVIMED entdecken
Open Access

Emergent social conventions and collective bias in LLM populations

Ariel Flint Ashery iD, Luca Maria Aiello iD, Andrea Baronchelli iD

Science Advances · 16.05.2025 · 11 (20)

DOI: 10.1126/sciadv.adu9368 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 16.05.2025. Verfasst von Ariel Flint Ashery und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, City St George's, University of London, Northampton Square, London EC1V 0HB, UK. Hauptthemen laut MEDLINE: Artificial Intelligence, Language, Social Behavior. Die Arbeit wurde bisher 88-mal zitiert (Crossref) und nennt 86 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Social conventions are the backbone of social coordination, shaping how individuals form a group. As growing populations of artificial intelligence (AI) agents communicate through natural language, a fundamental question is whether they can bootstrap the foundations of a society. Here, we present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents. We then show how strong collective biases can emerge during this process, even when agents exhibit no bias individually. Last, we examine how committed minority groups of adversarial LLM agents can drive social change by imposing alternative social conventions on the larger population. Our results show that AI systems can autonomously develop social conventions without explicit programming and have implications for designing AI systems that align, and remain aligned, with human values and societal goals.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceLanguageSocial BehaviorHumansModels, Theoretical

Autor:innen und Institutionen

  • Department of Mathematics, City St George's, University of London, Northampton Square, London EC1V 0HB, UK.
  • Computer Science Department, IT University of Copenhagen, Rued Langgaards Vej 7, 2300 Copenhagen, Denmark.
  • Pioneer Centre for AI, 3 Øster Voldgade, 1350 Copenhagen, Denmark.
  • The Alan Turing Institute, British Library, 96 Euston Road, London NW1 2DB, UK.

ORCID-Profile: Ariel Flint Ashery, Luca Maria Aiello, Andrea Baronchelli

Zitieren

APA

Ashery, A. F., Aiello, L. M., & Baronchelli, A. (2025). Emergent social conventions and collective bias in LLM populations. Science Advances, 11(20). https://doi.org/10.1126/sciadv.adu9368

Vancouver

Ashery AF, Aiello LM, Baronchelli A. Emergent social conventions and collective bias in LLM populations. Science Advances. 2025;11(20). doi:10.1126/sciadv.adu9368

BibTeX
@article{Ashery2025,
  author = {Ashery, Ariel Flint and Aiello, Luca Maria and Baronchelli, Andrea},
  title = {Emergent social conventions and collective bias in LLM populations},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {20},
  doi = {10.1126/sciadv.adu9368}
}
Kostenlos starten →