Network Effects and Agreement Drift in LLM Debates

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cau, Erica, Failla, Andrea, Rossetti, Giulio
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918448097918976
author Cau, Erica
Failla, Andrea
Rossetti, Giulio
author_facet Cau, Erica
Failla, Andrea
Rossetti, Giulio
contents Large Language Models (LLMs) have demonstrated an unprecedented ability to simulate human-like social behaviors, making them useful tools for simulating complex social systems. However, it remains unclear to what extent these simulations can be trusted to accurately capture key social mechanisms, particularly in highly unbalanced contexts involving minority groups. This paper uses a network generation model with controlled homophily and class sizes to examine how LLM agents behave collectively in multi-round debates. Moreover, our findings highlight a particular directional susceptibility that we term \textit{agreement drift}, in which agents are more likely to shift toward specific positions on the opinion scale. Overall, our findings highlight the need to disentangle structural effects from model biases before treating LLM populations as behavioral proxies for human groups.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11312
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Network Effects and Agreement Drift in LLM Debates
Cau, Erica
Failla, Andrea
Rossetti, Giulio
Social and Information Networks
Artificial Intelligence
Computers and Society
Multiagent Systems
Physics and Society
Large Language Models (LLMs) have demonstrated an unprecedented ability to simulate human-like social behaviors, making them useful tools for simulating complex social systems. However, it remains unclear to what extent these simulations can be trusted to accurately capture key social mechanisms, particularly in highly unbalanced contexts involving minority groups. This paper uses a network generation model with controlled homophily and class sizes to examine how LLM agents behave collectively in multi-round debates. Moreover, our findings highlight a particular directional susceptibility that we term \textit{agreement drift}, in which agents are more likely to shift toward specific positions on the opinion scale. Overall, our findings highlight the need to disentangle structural effects from model biases before treating LLM populations as behavioral proxies for human groups.
title Network Effects and Agreement Drift in LLM Debates
topic Social and Information Networks
Artificial Intelligence
Computers and Society
Multiagent Systems
Physics and Society
url https://arxiv.org/abs/2604.11312