Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning
This work addresses the challenge of improving zero-shot personalization and interpretability for social scientists in cultural value survey simulation, representing a domain-specific advancement.
The paper tackles the problem of simulating cultural value survey responses by introducing MARK, a multi-stage reasoning framework that uses personality-driven cognitive reasoning based on MBTI type dynamics theory. The system achieves 10% higher accuracy than existing baselines on the World Values Survey and reduces divergence between model predictions and human preferences.
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.