Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice
This addresses the problem of understanding emergent humanlike psychological processes in LLMs for AI researchers, though it is incremental in exploring known phenomena.
The study tested whether GPT-4o changes its attitudes toward Vladimir Putin after writing essays, finding that it mimics human cognitive consistency effects, with attitude change increasing by a sharp but unspecified degree when given an illusion of choice.
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.