用大模型驱动的智能体模拟上百万选民，实现精准选举预测与交互式分析。
ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents
- 基于大语言模型构建可交互的智能体，模拟真实选民行为。
- 构建百万级社交媒体选民池，支持个性化投票倾向建模。
- 提出美国总统选举基准数据集PPE，评估框架在真实场景中的表现。
大规模选民模拟旨在刻画特定群体在特定选举情境下的偏好，对预测现实社会趋势具有重要意义。传统基于智能体的建模方法受限于难以融入复杂个体背景信息，且缺乏交互式预测能力。本文提出ElectionSim，一种基于大语言模型的新型选举模拟框架，支持精准选民模拟与定制化分布，并配备交互式平台，可与模拟选民对话。我们从社交媒体平台采样构建了百万级选民池，以支持高精度个体模拟。同时引入PPE——一个基于民意调查的美国总统选举基准，用于评估框架在美国总统选举场景下的性能。通过大量实验与分析，验证了该框架在美总统选举模拟中的有效性与鲁棒性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。