Distributional Alignment for Social Simulation with LLMs: A Prompt Mixture Modeling Approach

Yutong Xie, Ruoyi Gao, Qiaozhu Mei

Keywords: Social Simulation, Distributional Alignment, Mixture Modeling, LLMs, System Prompt, Pluralistic Alignment

TL;DR: This paper introduces a novel prompt mixture modeling approach for social simulation, allowing for a nuanced and accurate simulation of diverse social populations.

Abstract: Social simulation is crucial for understanding complex population dynamics across various disciplines. Recent advancements in large language models (LLMs) have significantly boosted this field. However, a persistent challenge remains, that is to accurately capture the inherent distributional diversity of social activities. In this work, we propose a novel methodology for distributional alignment in social simulation by modeling social behavior or social attribute distributions as a mixture of system prompts. We introduce expectation-maximization (EM) and gradient boosting algorithms specifically designed for LLMs to efficiently identify the effective prompt mixtures. We demonstrate superior performance in two fundamental social simulation tasks: simulating personality traits and economic behaviors. Compared to existing approaches, our method significantly reduces disparities in the simulated populations, yielding distributions that closely match the observed realistic data. Our tool offers a robust solution for accurately simulating diverse social populations, promising to facilitate advancements across social sciences and related fields.

Submission Number: 22