Spiral of Silence in Large Language Model Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908580317233152 |
|---|---|
| author | Zhong, Mingze Fang, Meng Shi, Zijing Huang, Yuxuan Zheng, Shunfeng Du, Yali Chen, Ling Wang, Jun |
| author_facet | Zhong, Mingze Fang, Meng Shi, Zijing Huang, Yuxuan Zheng, Shunfeng Du, Yali Chen, Ling Wang, Jun |
| contents | The Spiral of Silence (SoS) theory holds that individuals with minority views often refrain from speaking out for fear of social isolation, enabling majority positions to dominate public discourse. When the 'agents' are large language models (LLMs), however, the classical psychological explanation is not directly applicable, since SoS was developed for human societies. This raises a central question: can SoS-like dynamics nevertheless emerge from purely statistical language generation in LLM collectives? We propose an evaluation framework for examining SoS in LLM agents. Specifically, we consider four controlled conditions that systematically vary the availability of 'History' and 'Persona' signals. Opinion dynamics are assessed using trend tests such as Mann-Kendall and Spearman's rank, along with concentration measures including kurtosis and interquartile range. Experiments across open-source and closed-source models show that history and persona together produce strong majority dominance and replicate SoS patterns; history signals alone induce strong anchoring; and persona signals alone foster diverse but uncorrelated opinions, indicating that without historical anchoring, SoS dynamics cannot emerge. The work bridges computational sociology and responsible AI design, highlighting the need to monitor and mitigate emergent conformity in LLM-agent systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02360 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spiral of Silence in Large Language Model Agents Zhong, Mingze Fang, Meng Shi, Zijing Huang, Yuxuan Zheng, Shunfeng Du, Yali Chen, Ling Wang, Jun Computation and Language Artificial Intelligence The Spiral of Silence (SoS) theory holds that individuals with minority views often refrain from speaking out for fear of social isolation, enabling majority positions to dominate public discourse. When the 'agents' are large language models (LLMs), however, the classical psychological explanation is not directly applicable, since SoS was developed for human societies. This raises a central question: can SoS-like dynamics nevertheless emerge from purely statistical language generation in LLM collectives? We propose an evaluation framework for examining SoS in LLM agents. Specifically, we consider four controlled conditions that systematically vary the availability of 'History' and 'Persona' signals. Opinion dynamics are assessed using trend tests such as Mann-Kendall and Spearman's rank, along with concentration measures including kurtosis and interquartile range. Experiments across open-source and closed-source models show that history and persona together produce strong majority dominance and replicate SoS patterns; history signals alone induce strong anchoring; and persona signals alone foster diverse but uncorrelated opinions, indicating that without historical anchoring, SoS dynamics cannot emerge. The work bridges computational sociology and responsible AI design, highlighting the need to monitor and mitigate emergent conformity in LLM-agent systems. |
| title | Spiral of Silence in Large Language Model Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.02360 |