Network Effects and Agreement Drift in LLM Debates

2026-04-13

AI Summary

This study investigates whether large language models (LLMs) can accurately capture critical social mechanisms of minority groups when simulating highly imbalanced social systems. To this end, the authors develop a network generation model that enables controlled manipulation of homophily and group size, integrated with a multi-agent LLM debate framework and opinion trajectory tracking to simulate opinion dynamics over multiple rounds of collective discussion. The work identifies and formally defines a novel phenomenon termed “consensus drift,” revealing a systematic bias in LLM-driven opinion formation. Results demonstrate that collective behaviors emerging from LLM agents are susceptible to inherent model biases, underscoring the necessity of disentangling structural social effects from artifacts introduced by the models themselves when employing LLMs as proxies for human behavior.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Natural Language Processing: (Large) Language Models

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Network Effects
• Agreement Drift
• Large Language Models
• Social Simulation
• Minority Groups

Innovation

• agreement drift
• network effects
• LLM debates
• homophily
• agent-based simulation