Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?
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_ | 1866917513993912320 |
|---|---|
| author | Vijjini, Anvesh Rao Manjunath, Sagar Chaturvedi, Snigdha |
| author_facet | Vijjini, Anvesh Rao Manjunath, Sagar Chaturvedi, Snigdha |
| contents | Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit similar behaviors when assigned high or low status personas. Using personas from diverse professions, we simulate multi turn, power asymmetric dialogues (e.g., principal teacher, justice lawyer) and measure (i) language coordination, (ii) pronoun usage, (iii) persuasion success, and (iv) compliance with unsafe requests. Our results show that LLMs show key socio-cognitive effects of power, albeit with nuances and variability, linking simulated interactions to both desirable and unsafe behaviors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17694 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations? Vijjini, Anvesh Rao Manjunath, Sagar Chaturvedi, Snigdha Computation and Language Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit similar behaviors when assigned high or low status personas. Using personas from diverse professions, we simulate multi turn, power asymmetric dialogues (e.g., principal teacher, justice lawyer) and measure (i) language coordination, (ii) pronoun usage, (iii) persuasion success, and (iv) compliance with unsafe requests. Our results show that LLMs show key socio-cognitive effects of power, albeit with nuances and variability, linking simulated interactions to both desirable and unsafe behaviors. |
| title | Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.17694 |