ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models

Researchers propose ExpertIVS, a framework using 14 Sociological Expert Agents to interpret World Values Survey responses, achieving 90.78% value restoration fidelity and outperforming baselines by 5.3% in value generalization across 480 individuals from 12 countries, enabling more accurate individual value simulation in large language models.

arXiv:2608.20355v1 Announce Type: new Abstract: Large Language Model LLM agents have demonstrated considerable potential for social simulation, yet struggle to accurately model individual value systems. Most existing methods mechanically stitch survey responses into prompts, which suffer from semantic fragmentation, failing to capture the internal coherence of human value systems. The value systems of LLMs are typically assessed using static multiple-choice questions, which fail to evaluate the value orientation in real-world dialogue interactions. To address these issues, we propose ExpertIVS, a framework employing 14 Sociological Expert Agents to interpret World Values Survey WVS responses through structured professional perspectives, rather than direct responses concatenation. These expert agents perform deep semantic reconstruction to generate robust and internally consistent individual profiles. To evaluate the consistency between LLMs and individual value systems during dynamic interactions, we further introduce a multi-agent debate mechanism. Extensive experiments across 480 individuals from 12 countries demonstrate that ExpertIVS achieves 90.78% value restoration fidelity and significantly outperforms baselines in value generalization +5.3% . Moreover, ExpertIVS exhibits strong personality discriminability and behavioral consistency, enabling a shift from mere response concatenation to genuine sociological role-playing.