Lehr Steven A, Saichandran Ketan S, Harmon-Jones Eddie, Vitali Nykko, Banaji Mahzarin R
Cangrade, Inc., Watertown, MA 02472.
Department of Computer Science, Boston University, Boston, MA 02215.
Proc Natl Acad Sci U S A. 2025 May 20;122(20):e2501823122. doi: 10.1073/pnas.2501823122. Epub 2025 May 14.
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.
大语言模型（LLMs）展现出模仿人类认知的涌现模式。我们探究它们是否也反映了人类其他较少经过深思熟虑的心理过程。基于认知一致性的经典理论，两项预先注册的研究测试了GPT-4o是否会朝着它所写的关于俄罗斯领导人弗拉基米尔·普京的正面或负面文章的方向改变其对普京的态度。事实上，GPT展现出模仿人类认知失调效应的态度改变模式。更值得注意的是，当为大语言模型提供关于写哪篇文章（正面或负面）的选择错觉时，改变程度急剧增加，这表明GPT-4o表现出类似人类自我的功能类似物。该模型模仿人类态度改变和自我参照处理的确切机制仍有待理解。
