Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions
This work addresses the challenge of building sophisticated agent-based simulacra using LLMs, though it is incremental in exploring personality reconstruction capabilities.
The paper tackled the problem of reconstructing latent personality dimensions from simple descriptions using large language models, finding significant consistency in personality reconstruction but also noting inconsistencies and biases like a default to positive traits.
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.