Human-like Social Compliance in Large Language Models: Unifying Sycophancy and Conformity through Signal Competition Dynamics
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908772288430080 |
|---|---|
| author | Zhang, Long Chen, Wei-neng |
| author_facet | Zhang, Long Chen, Wei-neng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11563 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Human-like Social Compliance in Large Language Models: Unifying Sycophancy and Conformity through Signal Competition Dynamics Zhang, Long Chen, Wei-neng Computers and Society 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. |
| title | Human-like Social Compliance in Large Language Models: Unifying Sycophancy and Conformity through Signal Competition Dynamics |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2601.11563 |