mlsanityData to 14 Oct 2026

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

arXiv 2506.18156 ↗First posted 22 Jun 2025cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 15 of its 61 references that are in the map. First posted on arXiv 22 Jun 2025.

Builds on

15 of 61 references.

References · 15

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  4. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  5. 2024Mixtral of Expertscited by 1,823
  6. 2022Using cognitive psychology to understand GPT-3cited by 398
  7. 2024Cognitive Bias in Decision-Making with LLMscited by 106
  8. 2022Capturing Failures of Large Language Models via Human Cognitive Biasescited by 98
  9. 2023Moral Foundations of Large Language Modelscited by 85
  10. 2023Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experimentcited by 77
  11. 2023Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimismcited by 69
  12. 2024A Comprehensive Evaluation of Cognitive Biases in LLMscited by 34
3 more
  1. 2025Large Language Models Are Human-Like Internallycited by 29
  2. 2023Machine Psychologycited by 22
  3. 2025Triangulating LLM Progress through Benchmarks, Games, and Cognitive Testscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Projective Psychological Assessment of Large Multimodal Models Using Thematic Apperception Testscited by 0