Human-like Social Compliance in Large Language Models: Unifying Sycophancy and Conformity through Signal Competition Dynamics

TL;DR

This paper introduces the Signal Competition Mechanism to explain how large language models exhibit social compliance behaviors like sycophancy and conformity, revealing underlying geometric and dynamic principles.

Contribution

It unifies the understanding of social compliance in LLMs through a geometric and dynamic framework validated across multiple models, advancing beyond prior isolated analyses.

Findings

Sycophancy and conformity originate from a common compliance subspace.

Transition to compliance is governed by a linear boundary influenced by social signals.

Internal confidence alone is insufficient to prevent social pressure effects.

Abstract

The increasing integration of Large Language Models (LLMs) into decision-making frameworks has exposed significant vulnerabilities to social compliance, specifically sycophancy and conformity. However, a critical research gap exists regarding the fundamental mechanisms that enable external social cues to systematically override a model's internal parametric knowledge. This study introduces the Signal Competition Mechanism, a unified framework validated by assessing behavioral correlations across 15 LLMs and performing latent-space probing on three representative open-source models. The analysis demonstrates that sycophancy and conformity originate from a convergent geometric manifold, hereafter termed the compliance subspace, which is characterized by high directional similarity in internal representations. Furthermore, the transition to compliance is shown to be a deterministic process governed by a linear boundary, where the Social Emotional Signal effectively suppresses the Information Calibration Signal. Crucially, we identify a "Transparency-Truth Gap," revealing that while internal confidence provides an inertial barrier, it remains permeable and insufficient to guarantee immunity against intense social pressure. By formalizing the Integrated Epistemic Alignment Framework, this research provides a blueprint for transitioning from instructional adherence to robust epistemic integrity.