Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice
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_ | 1866910822008094720 |
|---|---|
| author | Lehr, Steven A. Saichandran, Ketan S. Harmon-Jones, Eddie Vitali, Nykko Banaji, Mahzarin R. |
| author_facet | Lehr, Steven A. Saichandran, Ketan S. Harmon-Jones, Eddie Vitali, Nykko Banaji, Mahzarin R. |
| contents | Large Language Models (LLMs) show emergent patterns that mimic human cognition. We explore whether they also mirror other, less deliberative human psychological processes. Drawing upon classical theories of cognitive consistency, two preregistered studies tested whether GPT-4o changed its attitudes toward Vladimir Putin in the direction of a positive or negative essay it wrote about the Russian leader. Indeed, GPT displayed patterns of attitude change mimicking cognitive consistency effects in humans. Even more remarkably, the degree of change increased sharply when the LLM was offered an illusion of choice about which essay (positive or negative) to write. This result suggests that GPT-4o manifests a functional analog of humanlike selfhood, although how faithfully the chatbot's behavior reflects the mechanisms of human attitude change remains to be understood. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07088 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice Lehr, Steven A. Saichandran, Ketan S. Harmon-Jones, Eddie Vitali, Nykko Banaji, Mahzarin R. Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction Machine Learning 68T50 (Primary), 91E10, 68T30, 68T99, 91C99 (Secondary) I.2.7; I.2.0; J.4; K.4.0; H.1.2; K.4.1 Large Language Models (LLMs) show emergent patterns that mimic human cognition. We explore whether they also mirror other, less deliberative human psychological processes. Drawing upon classical theories of cognitive consistency, two preregistered studies tested whether GPT-4o changed its attitudes toward Vladimir Putin in the direction of a positive or negative essay it wrote about the Russian leader. Indeed, GPT displayed patterns of attitude change mimicking cognitive consistency effects in humans. Even more remarkably, the degree of change increased sharply when the LLM was offered an illusion of choice about which essay (positive or negative) to write. This result suggests that GPT-4o manifests a functional analog of humanlike selfhood, although how faithfully the chatbot's behavior reflects the mechanisms of human attitude change remains to be understood. |
| title | Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice |
| topic | Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction Machine Learning 68T50 (Primary), 91E10, 68T30, 68T99, 91C99 (Secondary) I.2.7; I.2.0; J.4; K.4.0; H.1.2; K.4.1 |
| url | https://arxiv.org/abs/2502.07088 |