The massive population election simulation aims to model the preferences of specific groups in particular election scenarios. It has garnered significant attention for its potential to forecast real-world social trends. Traditional agent-based modeling (ABM) methods are constrained by their ability to incorporate complex individual background information and provide interactive prediction results. In this paper, we introduce ElectionSim, an innovative election simulation framework based on large language models, designed to support accurate voter simulations and customized distributions, together with an interactive platform to dialogue with simulated voters. We present a million-level voter pool sampled from social media platforms to support accurate individual simulation. We also introduce PPE, a poll-based presidential election benchmark to assess the performance of our framework under the U.S. presidential election scenario. Through extensive experiments and analyses, we demonstrate the effectiveness and robustness of our framework in U.S. presidential election simulations.

翻译：大规模人口选举模拟旨在刻画特定群体在特定选举情境中的偏好，因其预测现实社会趋势的潜力而备受关注。传统基于智能体的建模方法在整合复杂个体背景信息及提供交互式预测结果方面存在局限。本文提出ElectionSim，一种基于大语言模型的创新选举模拟框架，旨在支持精准的选民模拟与定制化分布，并配备可与模拟选民对话的交互平台。我们构建了从社交媒体平台采样的百万级选民池以支撑精准个体模拟。同时提出PPE基准——基于民意调查的总统选举评估体系，用于检验本框架在美国总统选举情境下的性能。通过大量实验与分析，我们验证了该框架在模拟美国总统选举中的有效性与鲁棒性。