Generative Personality Simulation via Theory-Informed Structured Interview

TL;DR

This paper introduces a novel method called PSI that incorporates psychological insights into LLMs to generate more diverse and human-like personality data, improving their utility in social science research.

Contribution

The paper presents a new psychometrically grounded approach, PSI, for enhancing LLMs' ability to simulate human-like personality data with greater heterogeneity.

Findings

PSI improves heterogeneity in LLM personality simulations

PSI predicts personality-related behavioral outcomes

Evaluation shows enhanced reliability and validity of simulated data

Abstract

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.