Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning

TL;DR

This paper presents MARK, a multi-stage reasoning framework inspired by MBTI theory, that improves the simulation of cultural value survey responses by incorporating personality-driven cognitive processes, leading to more accurate and interpretable models.

Contribution

Introduces MARK, a novel multi-stage reasoning framework that enhances survey response simulation by integrating personality-based cognitive reasoning inspired by psychological theories.

Findings

Outperforms existing models by 10% accuracy on the World Values Survey

Reduces divergence between model predictions and human preferences

Enhances zero-shot personalization and interpretability of survey simulations

Abstract

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.