ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912106717118464 |
|---|---|
| author | Zhang, Xinnong Lin, Jiayu Sun, Libo Qi, Weihong Yang, Yihang Chen, Yue Lyu, Hanjia Mou, Xinyi Chen, Siming Luo, Jiebo Huang, Xuanjing Tang, Shiping Wei, Zhongyu |
| author_facet | Zhang, Xinnong Lin, Jiayu Sun, Libo Qi, Weihong Yang, Yihang Chen, Yue Lyu, Hanjia Mou, Xinyi Chen, Siming Luo, Jiebo Huang, Xuanjing Tang, Shiping Wei, Zhongyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20746 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents Zhang, Xinnong Lin, Jiayu Sun, Libo Qi, Weihong Yang, Yihang Chen, Yue Lyu, Hanjia Mou, Xinyi Chen, Siming Luo, Jiebo Huang, Xuanjing Tang, Shiping Wei, Zhongyu Computation and Language Computers and Society Human-Computer Interaction 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. |
| title | ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents |
| topic | Computation and Language Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2410.20746 |