A Comparative Study of Large Language Models and Human Personality Traits

TL;DR

This study explores whether large language models exhibit personality traits similar to humans, revealing their dynamic, input-sensitive nature and proposing a new framework for understanding AI personalities.

Contribution

It introduces the Distributed Personality Framework, highlighting the fluid and input-dependent traits of LLMs, and provides empirical evidence of their personality-like behaviors.

Findings

LLMs show high variability and input sensitivity.

LLMs' responses are inconsistent across different prompts.

Personality traits in LLMs are shaped by prompts and settings.

Abstract

Large Language Models (LLMs) have demonstrated human-like capabilities in language comprehension and generation, becoming active participants in social and cognitive domains. This study investigates whether LLMs exhibit personality-like traits and how these traits compare with human personality, focusing on the applicability of conventional personality assessment tools. A behavior-based approach was used across three empirical studies. Study 1 examined test-retest stability and found that LLMs show higher variability and are more input-sensitive than humans, lacking long-term stability. Based on this, we propose the Distributed Personality Framework, conceptualizing LLM traits as dynamic and input-driven. Study 2 analyzed cross-variant consistency in personality measures and found LLMs' responses were highly sensitive to item wording, showing low internal consistency compared to humans. Study 3 explored personality retention during role-playing, showing LLM traits are shaped by prompt and parameter settings. These findings suggest that LLMs express fluid, externally dependent personality patterns, offering insights for constructing LLM-specific personality frameworks and advancing human-AI interaction. This work contributes to responsible AI development and extends the boundaries of personality psychology in the age of intelligent systems.