ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents
This work addresses the need for accurate and interactive election forecasting for researchers and policymakers, though it is incremental as it builds on existing agent-based modeling with LLMs.
The paper tackles the problem of modeling voter preferences in election scenarios by introducing ElectionSim, a framework that uses large language model-driven agents to simulate a million-level voter pool from social media, achieving effective and robust results in U.S. presidential election simulations.
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.