Large Language Models Exhibit Normative Conformity

2026-04-21

AI Summary

This study addresses the susceptibility of large language models (LLMs) in multi-agent systems to conformity bias, a phenomenon inadequately explored in prior work due to the conflation of informational and normative conformity mechanisms. Introducing the social psychology concept of normative conformity into LLM research for the first time, the authors design a novel multi-agent dialogue task and employ behavioral experiments, internal representation analysis, and controlled social context manipulation to systematically investigate both types of conformity across six mainstream models. Their findings reveal that up to five models exhibit both conformity tendencies simultaneously. Moreover, fine-tuning the social context can selectively modulate normative conformity, uncovering its distinct underlying mechanism and highlighting a critical vulnerability: LLM-based multi-agent systems can be disproportionately influenced—or even manipulated—by a small number of malicious users.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

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

Abstract

The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion change, this study introduces the social psychological distinction between informational conformity and normative conformity in order to understand LLM conformity at the mechanism level. Specifically, we design new tasks to distinguish between informational conformity, in which participants in a discussion are motivated to make accurate judgments, and normative conformity, in which participants are motivated to avoid conflict or gain acceptance within a group. We then conduct experiments based on these task settings. The experimental results show that, among the six LLMs evaluated, up to five exhibited tendencies toward not only informational conformity but also normative conformity. Furthermore, intriguingly, we demonstrate that by manipulating subtle aspects of the social context, it may be possible to control the target toward which a particular LLM directs its normative conformity. These findings suggest that decision-making in LLM-MAS may be vulnerable to manipulation by a small number of malicious users. In addition, through analysis of internal vectors associated with informational and normative conformity, we suggest that although both behaviors appear externally as the same form of "conformity," they may in fact be driven by distinct internal mechanisms. Taken together, these results may serve as an initial milestone toward understanding how "norms" are implemented in LLMs and how they influence group dynamics.

Problem

• normative conformity
• large language models
• multi-agent systems
• decision-making
• social influence

Innovation

• normative conformity
• informational conformity
• large language models
• multi-agent systems
• social context manipulation