Semantic Scholar Open Access 2024 31 sitasi

Political-LLM: Large Language Models in Political Science

Lincan Li Jiaqi Li Catherine Chen Fred Gui Hongjian Yang +42 lainnya

Abstrak

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer science and political science--present the first principled framework termed Political-LLM to advance the comprehensive understanding of integrating LLMs into computational political science. Specifically, we first introduce a fundamental taxonomy classifying the existing explorations into two perspectives: political science and computational methodologies. In particular, from the political science perspective, we highlight the role of LLMs in automating predictive and generative tasks, simulating behavior dynamics, and improving causal inference through tools like counterfactual generation; from a computational perspective, we introduce advancements in data preparation, fine-tuning, and evaluation methods for LLMs that are tailored to political contexts. We identify key challenges and future directions, emphasizing the development of domain-specific datasets, addressing issues of bias and fairness, incorporating human expertise, and redefining evaluation criteria to align with the unique requirements of computational political science. Political-LLM seeks to serve as a guidebook for researchers to foster an informed, ethical, and impactful use of Artificial Intelligence in political science. Our online resource is available at: http://political-llm.org/.

Topik & Kata Kunci

Penulis (47)

L

Lincan Li

J

Jiaqi Li

C

Catherine Chen

F

Fred Gui

H

Hongjian Yang

C

Chenxiao Yu

Z

Zhengguang Wang

J

J. Cai

J

Junlong Zhou

B

Bolin Shen

A

Alexander Qian

W

Weixin Chen

Z

Zhongkai Xue

L

Lichao Sun

L

Lifang He

H

Hanjie Chen

K

Kaize Ding

Z

Zijia Du

F

Fangzhou Mu

J

Jiaxin Pei

J

Jieyu Zhao

S

Swabha Swayamdipta

W

Willie Neiswanger

H

Hua Wei

X

Xiyang Hu

S

Shixiang Zhu

T

Tian-Xiang Chen

Y

Ying-Liang Lu

Y

Yang Shi

L

Li Qin

T

Tianfan Fu

Z

Zhengzhong Tu

Y

Yuzhe Yang

J

Jaemin Yoo

J

Jiaheng Zhang

R

Ryan A. Rossi

L

Liang Zhan

L

Liangxuan Zhao

E

Emilio Ferrara

Y

Yan Liu

F

Furong Huang

X

Xiangliang Zhang

L

L. Rothenberg

S

Shuiwang Ji

P

Philip S. Yu

Y

Yue Zhao

Y

Yushun Dong

Format Sitasi

Li, L., Li, J., Chen, C., Gui, F., Yang, H., Yu, C. et al. (2024). Political-LLM: Large Language Models in Political Science. https://doi.org/10.48550/arXiv.2412.06864

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.48550/arXiv.2412.06864
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Total Sitasi
31×
Sumber Database
Semantic Scholar
DOI
10.48550/arXiv.2412.06864
Akses
Open Access ✓