Kernels of selfhood: GPT-4o shows humanlike patterns of cognitive dissonance moderated by free choice
Proceedings of the National Academy of Sciences · 20.05.2025 · 122 (20)
DOI: 10.1073/pnas.2501823122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 14.05.2025. Verfasst von Steven A Lehr und 4 weiteren Autor:innen. Beteiligte Einrichtung: Cangrade, Inc., Watertown, MA 02472. Hauptthemen laut MEDLINE: Cognitive Dissonance, Choice Behavior, Language, Cognition. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
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 dissonance 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, suggesting that GPT-4o manifests a functional analog of humanlike selfhood. The exact mechanisms by which the model mimics human attitude change and self-referential processing remain to be understood.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cangrade, Inc., Watertown, MA 02472.
- Department of Computer Science, Boston University, Boston, MA 02215.
- School of Psychology, The University of New South Wales, Sydney, NSW 2052, Australia.
- Department of Psychology, Harvard University, Cambridge, MA 02138.
ORCID-Profile: Steven A Lehr, Mahzarin R Banaji
Zitieren
APA
Lehr, S. A., Saichandran, K. S., Harmon-Jones, E., Vitali, N., & Banaji, M. R. (2025). Kernels of selfhood: GPT-4o shows humanlike patterns of cognitive dissonance moderated by free choice. Proceedings of the National Academy of Sciences, 122(20). https://doi.org/10.1073/pnas.2501823122
Vancouver
Lehr SA, Saichandran KS, Harmon-Jones E, Vitali N, Banaji MR. Kernels of selfhood: GPT-4o shows humanlike patterns of cognitive dissonance moderated by free choice. Proceedings of the National Academy of Sciences. 2025;122(20). doi:10.1073/pnas.2501823122
BibTeX
@article{Lehr2025,
author = {Lehr, Steven A and Saichandran, Ketan S and Harmon-Jones, Eddie and Vitali, Nykko and Banaji, Mahzarin R},
title = {Kernels of selfhood: GPT-4o shows humanlike patterns of cognitive dissonance moderated by free choice},
journal = {Proceedings of the National Academy of Sciences},
year = {2025},
volume = {122},
number = {20},
doi = {10.1073/pnas.2501823122}
}
EUVIMED