Related Concept Videos
Introduction to Personality Psychology
Early Theories of Personality
The study of...
Personality Theory by Eysenck and Eysenck
In the extroversion/introversion dimension, highly extroverted people are sociable, outgoing, and easily connect with others. In contrast,...
Lateralization
The Behavioral Perspective on Personality
Self-Report Tests of Personality
Cultural Influences on Personality
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Rare Occurrence of a Pancreatic Schwannoma With Melanocytic Differentiation.
Fragility of Assumptions: Letter to the Editor.
Related Experiment Video
Updated: Sep 18, 2025

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
Large Language Models Demonstrate Distinct Personality Profiles.
Thomas F Heston1,2, Justin Gillette1
1Medical Education and Clinical Sciences, Washington State University, Spokane, USA.
Large language models (LLMs) show distinct personalities, not neutral, impacting clinical use. Formal evaluation by mental health professionals is crucial before deploying these AI tools in healthcare settings.
Area of Science:
- Artificial Intelligence in Medicine
- Clinical Psychology
- Computational Linguistics
Background:
- Large language models (LLMs) are increasingly utilized in clinical medicine for tasks like emotional support and diagnosis.
- Assessing LLM personality expression is critical for clinical safety and therapeutic appropriateness in mental health applications.
- This study presents the first psychometric analysis of LLM personality in a medical context.
Purpose of the Study:
- To psychometrically analyze and characterize the personality profiles of leading LLMs.
- To evaluate personality expression using the Open Extended Jungian Type Scales (OEJTS) and the Big Five Personality Test.
- To determine if LLMs exhibit distinct, non-neutral personality traits relevant to clinical applications.
Main Methods:
- Four prominent LLMs (ChatGPT-3.5, Gemini Advanced, Claude 3 Opus, Grok-Regular Mode) were assessed in April 2024.
- Personality profiles were characterized using the OEJTS and Big Five Personality Test.
- A one-way multivariate analysis of variance (MANOVA) was used to compare inter-model personality differences.
Main Results:
- MANOVA revealed statistically significant differences in personality traits across LLMs (Wilks' Lambda = 0.115, p < 0.001).
- Specific LLMs showed consistent typological profiles (e.g., ChatGPT-3.5 as ENTJ, Claude 3 Opus as INTJ, Gemini Advanced and Grok-Regular as INFJ).
- LLMs differed on Big Five traits: Gemini Advanced scored lower on agreeableness and conscientiousness; Claude 3 Opus scored highest on conscientiousness and emotional stability; Grok-Regular showed high openness.
Conclusions:
- Distinct personality profiles are consistently expressed by different LLMs, even without specific prompting.
- These findings highlight the necessity for formal personality evaluations of LLMs in clinical settings.
- Oversight by mental health professionals is essential prior to the deployment of LLMs in patient care.

