Saved in:
Bibliographic Details
Main Authors: Hamada, Hiro Taiyo, Fujisawa, Ippei, Kawakita, Genji, Yamada, Yuki
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.23055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916815165194240
author Hamada, Hiro Taiyo
Fujisawa, Ippei
Kawakita, Genji
Yamada, Yuki
author_facet Hamada, Hiro Taiyo
Fujisawa, Ippei
Kawakita, Genji
Yamada, Yuki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23055
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Measuring How LLMs Internalize Human Psychological Concepts: A preliminary analysis
Hamada, Hiro Taiyo
Fujisawa, Ippei
Kawakita, Genji
Yamada, Yuki
Machine Learning
Artificial Intelligence
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.
title Measuring How LLMs Internalize Human Psychological Concepts: A preliminary analysis
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.23055