Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2502.12109 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911385438388224 |
|---|---|
| author | Wang, Pengda Zou, Huiqi Jiang, Han Chen, Hanjie Sun, Tianjun Yi, Xiaoyuan Xiao, Ziang Oswald, Frederick L. |
| author_facet | Wang, Pengda Zou, Huiqi Jiang, Han Chen, Hanjie Sun, Tianjun Yi, Xiaoyuan Xiao, Ziang Oswald, Frederick L. |
| contents | Despite their potential as human proxies, LLMs often fail to generate heterogeneous data with human-like diversity, thereby diminishing their value in advancing social science research. To address this gap, we propose a novel method to incorporate psychological insights into LLM simulation through the Personality Structured Interview (PSI). PSI leverages psychometric scale-development procedures to capture personality-related linguistic information from a formal psychological perspective. To systematically evaluate simulation fidelity, we developed a measurement theory grounded evaluation procedure that considers the latent construct nature of personality and evaluates its reliability, structural validity, and external validity. Results from three experiments demonstrate that PSI effectively improves human-like heterogeneity in LLM-simulated personality data and predicts personality-related behavioral outcomes. We further offer a theoretical framework for designing theory-informed structured interviews to enhance the reliability and effectiveness of LLMs in simulating human-like data for broader psychometric research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12109 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generative Personality Simulation via Theory-Informed Structured Interview Wang, Pengda Zou, Huiqi Jiang, Han Chen, Hanjie Sun, Tianjun Yi, Xiaoyuan Xiao, Ziang Oswald, Frederick L. Computation and Language Artificial Intelligence Despite their potential as human proxies, LLMs often fail to generate heterogeneous data with human-like diversity, thereby diminishing their value in advancing social science research. To address this gap, we propose a novel method to incorporate psychological insights into LLM simulation through the Personality Structured Interview (PSI). PSI leverages psychometric scale-development procedures to capture personality-related linguistic information from a formal psychological perspective. To systematically evaluate simulation fidelity, we developed a measurement theory grounded evaluation procedure that considers the latent construct nature of personality and evaluates its reliability, structural validity, and external validity. Results from three experiments demonstrate that PSI effectively improves human-like heterogeneity in LLM-simulated personality data and predicts personality-related behavioral outcomes. We further offer a theoretical framework for designing theory-informed structured interviews to enhance the reliability and effectiveness of LLMs in simulating human-like data for broader psychometric research. |
| title | Generative Personality Simulation via Theory-Informed Structured Interview |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.12109 |