Opinion dynamics and mutual influence with LLM agents through dialog simulation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915796445298688 |
|---|---|
| author | He, Yulong Zhang, Dutao Kovalchuk, Sergey Li, Pengyi Sedakov, Artem |
| author_facet | He, Yulong Zhang, Dutao Kovalchuk, Sergey Li, Pengyi Sedakov, Artem |
| contents | A fundamental challenge in opinion dynamics research is the scarcity of real-world longitudinal opinion data, which complicates the validation of theoretical models. To address this, we propose a novel simulation framework using large language model (LLM) agents in structured multi-round dialogs. Each agent's dialog history is iteratively updated with its own previously stated opinions and those of others analogous to the classical DeGroot model. Furthermore, by retaining each agent's initial opinion throughout the dialog, we simulate anchoring effects consistent with the Friedkin-Johnsen model of opinion dynamics. Our framework thus bridges classical opinion dynamics models and modern multi-agent LLM systems, providing a scalable tool for simulating and analyzing opinion formation when real-world data is limited or inaccessible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12583 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Opinion dynamics and mutual influence with LLM agents through dialog simulation He, Yulong Zhang, Dutao Kovalchuk, Sergey Li, Pengyi Sedakov, Artem Computer Science and Game Theory A fundamental challenge in opinion dynamics research is the scarcity of real-world longitudinal opinion data, which complicates the validation of theoretical models. To address this, we propose a novel simulation framework using large language model (LLM) agents in structured multi-round dialogs. Each agent's dialog history is iteratively updated with its own previously stated opinions and those of others analogous to the classical DeGroot model. Furthermore, by retaining each agent's initial opinion throughout the dialog, we simulate anchoring effects consistent with the Friedkin-Johnsen model of opinion dynamics. Our framework thus bridges classical opinion dynamics models and modern multi-agent LLM systems, providing a scalable tool for simulating and analyzing opinion formation when real-world data is limited or inaccessible. |
| title | Opinion dynamics and mutual influence with LLM agents through dialog simulation |
| topic | Computer Science and Game Theory |
| url | https://arxiv.org/abs/2602.12583 |