AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology

TL;DR

This paper explores whether large language models display human-like cognitive patterns across four psychological frameworks, revealing similarities and differences in their reasoning, biases, and moral judgments.

Contribution

It introduces a novel evaluation methodology applying established psychological theories to assess LLMs' cognitive behaviors, highlighting their human-like tendencies and limitations.

Findings

Models produce coherent narratives and show framing biases.

Models exhibit moral judgments similar to human concerns.

Models demonstrate self-contradictions and rationalizations.

Abstract

We investigate whether Large Language Models (LLMs) exhibit human-like cognitive patterns under four established frameworks from psychology: Thematic Apperception Test (TAT), Framing Bias, Moral Foundations Theory (MFT), and Cognitive Dissonance. We evaluated several proprietary and open-source models using structured prompts and automated scoring. Our findings reveal that these models often produce coherent narratives, show susceptibility to positive framing, exhibit moral judgments aligned with Liberty/Oppression concerns, and demonstrate self-contradictions tempered by extensive rationalization. Such behaviors mirror human cognitive tendencies yet are shaped by their training data and alignment methods. We discuss the implications for AI transparency, ethical deployment, and future work that bridges cognitive psychology and AI safety