Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions

TL;DR

This study investigates whether large language models can accurately reconstruct an agent's latent personality traits from simple descriptions, revealing both promising consistency and notable biases influenced by socio-demographic factors.

Contribution

The paper demonstrates LLMs' ability to recover latent personality traits from minimal descriptions and highlights biases and influences of socio-demographic factors.

Findings

LLMs show significant consistency in personality reconstruction

Biases such as positivity tendency are observed in LLM outputs

Socio-demographic factors affect reconstructed personality dimensions

Abstract

Personality, a fundamental aspect of human cognition, contains a range of traits that influence behaviors, thoughts, and emotions. This paper explores the capabilities of large language models (LLMs) in reconstructing these complex cognitive attributes based only on simple descriptions containing socio-demographic and personality type information. Utilizing the HEXACO personality framework, our study examines the consistency of LLMs in recovering and predicting underlying (latent) personality dimensions from simple descriptions. Our experiments reveal a significant degree of consistency in personality reconstruction, although some inconsistencies and biases, such as a tendency to default to positive traits in the absence of explicit information, are also observed. Additionally, socio-demographic factors like age and number of children were found to influence the reconstructed personality dimensions. These findings have implications for building sophisticated agent-based simulacra using LLMs and highlight the need for further research on robust personality generation in LLMs.