Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning
Liu, Haijiang, Li, Qiyuan, Gao, Chao, Cao, Yong, Xu, Xiangyu, Wu, Xun, Hershcovich, Daniel, Gu, Jinguang
–arXiv.org Artificial Intelligence
Introducing MARK, the Multi-stAge Reasoning frameworK for cultural value survey response simulation, designed to enhance the accuracy, steerability, and interpretability of large language models in this task. The system is inspired by the type dynamics theory in the MBTI psychological framework for personality research. It effectively predicts and utilizes human demographic information for simulation: life-situational stress analysis, group-level personality prediction, and self-weighted cognitive imitation. Experiments on the World Values Survey show that MARK outperforms existing baselines by 10% accuracy and reduces the divergence between model predictions and human preferences. This highlights the potential of our framework to improve zero-shot personalization and help social scientists interpret model predictions.
arXiv.org Artificial Intelligence
Aug-26-2025
- Country:
- Asia
- China
- Guangdong Province > Guangzhou (0.04)
- Hong Kong (0.04)
- Hubei Province > Wuhan (0.04)
- Singapore (0.04)
- Thailand > Bangkok
- Bangkok (0.04)
- China
- Europe
- Croatia > Dubrovnik-Neretva County
- Dubrovnik (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Germany > Baden-Württemberg
- Tübingen Region > Tübingen (0.04)
- Croatia > Dubrovnik-Neretva County
- North America
- Canada > Ontario
- Toronto (0.04)
- Mexico > Mexico City
- Mexico City (0.04)
- United States > New Mexico
- Bernalillo County > Albuquerque (0.04)
- Canada > Ontario
- Asia
- Genre:
- Research Report > New Finding (0.67)
- Industry:
- Technology: