Saved in:
Bibliographic Details
Main Authors: Kundu, Akash, Goswami, Rishika
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.18156
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911313488248832
author Kundu, Akash
Goswami, Rishika
author_facet Kundu, Akash
Goswami, Rishika
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2506_18156
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology
Kundu, Akash
Goswami, Rishika
Artificial Intelligence
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
title AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology
topic Artificial Intelligence
url https://arxiv.org/abs/2506.18156