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

2025-08-25

AI Summary

This study addresses the low accuracy, limited controllability, and poor interpretability of large language models (LLMs) in simulating human responses to cultural value surveys. We propose MARK, a personality-driven, multi-stage cognitive reasoning framework. Methodologically, MARK integrates MBTI-type dynamics to jointly model individual personality traits, situational stressors, and cognitive preferences; introduces a personality-type dynamic mechanism for zero-shot personalized simulation; and employs a self-weighted cognitive imitation strategy to better approximate human preference distributions. Our key contributions are: (1) the first LLM reasoning architecture that synergistically integrates population-level personality prediction, life-context stress analysis, and cognitive imitation; and (2) empirical validation on the World Values Survey (WVS), where MARK achieves a 10% absolute accuracy improvement over state-of-the-art baselines and significantly reduces systematic prediction bias relative to ground-truth human responses—while preserving both interpretability and controllability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Learning Human Values and Preferences
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Simulating cultural value survey responses with personality-driven reasoning
• Enhancing accuracy and interpretability of large language models
• Reducing divergence between model predictions and human preferences

Innovation

• Multi-stage personality-driven cognitive reasoning framework
• MBTI-inspired type dynamics for personality simulation
• Self-weighted cognitive imitation for response generation