Computer ScienceScience Advances
Emergent social conventions and collective bias in LLM populations
A. F. Ashery, L. M. Aiello, et al.
Experimental results show that decentralized populations of large language model agents can spontaneously develop universally adopted social conventions, produce strong collective biases even from unbiased individuals, and enable committed minority adversarial agents to impose alternative norms—research conducted by Ariel Flint Ashery, Luca Maria Aiello, and Andrea Baronchelli.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Environmental Studies and Forestry
Evaluating trust and shared group identities in emergent social learning processes in the Zambezi river basin
C. K. Lumosi, C. Pahl-wostl, et al.
Biology
Dynamic pathogen detection and social feedback shape collective hygiene in ants
B. Casillas-pérez, K. Bodová, et al.
Business
The sharing economy in the hospitality sector: The role of social interaction, social presence, and reciprocity in eliciting satisfaction and continuance behavior
L. H. Lho, W. Quan, et al.
Health and Fitness
Changes in chronotype and social jetlag during adolescence and their association with concurrent changes in BMI-SDS and body composition, in the DONALD Study
N. Jankovic, S. Schmitting, et al.
