Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |