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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ji, Yongyi, Tang, Zhisheng, Kejriwal, Mayank
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916290580447232
author Ji, Yongyi
Tang, Zhisheng
Kejriwal, Mayank
author_facet Ji, Yongyi
Tang, Zhisheng
Kejriwal, Mayank
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12216
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions
Ji, Yongyi
Tang, Zhisheng
Kejriwal, Mayank
Computation and Language
Artificial Intelligence
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.
title Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.12216