# Measuring How LLMs Internalize Human Psychological Concepts: A preliminary analysis

arXiv: https://arxiv.org/abs/2506.23055 · HTML: https://mlsanity.com/paper/2506.23055/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 29 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [Premise Order Matters in Reasoning with Large Language Models](https://mlsanity.com/paper/2402.08939/) (2024)
- [Machine Psychology](https://mlsanity.com/paper/2303.13988/) (2023)
- [PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection](https://mlsanity.com/paper/2310.20256/) (2023)
- [Gromov-Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models](https://mlsanity.com/paper/2308.04381/) (2023)
- [Deep Lexical Hypothesis: Identifying personality structure in natural language](https://mlsanity.com/paper/2203.02092/) (2022)

## Abstract (arXiv)

Large Language Models (LLMs) such as ChatGPT have shown remarkable abilities in producing human-like text. However, it is unclear how accurately these models internalize concepts that shape human thought and behavior. Here, we developed a quantitative framework to assess concept alignment between LLMs and human psychological dimensions using 43 standardized psychological questionnaires, selected for their established validity in measuring distinct psychological constructs. Our method evaluates how accurately language models reconstruct and classify questionnaire items through pairwise similarity analysis. We compared resulting cluster structures with the original categorical labels using hierarchical clustering. A GPT-4 model achieved superior classification accuracy (66.2%), significantly outperforming GPT-3.5 (55.9%) and BERT (48.1%), all exceeding random baseline performance (31.9%). We also demonstrated that the estimated semantic similarity from GPT-4 is associated with Pearson's correlation coefficients of human responses in multiple psychological questionnaires. This framework provides a novel approach to evaluate the alignment of the human-LLM concept and identify potential representational biases. Our findings demonstrate that modern LLMs can approximate human psychological constructs with measurable accuracy, offering insights for developing more interpretable AI systems.