arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.11409cs.CL
收藏

大型语言模型政治样本模拟中的表征偏差

Representation Bias in Political Sample Simulations with Large Language Models

University of Rochester(罗切斯特大学)

Weihong Qi, Hanjia Lyu, Jiebo Luo

AI总结:

本研究利用GPT-3.5-Turbo模拟政治样本,识别并量化投票与舆论中的表征偏差,发现投票模拟优于舆论,英语国家、两党制和民主环境表现更佳。

摘要:

本研究旨在识别并量化使用大型语言模型模拟政治样本时的偏差,特别关注投票选择和公众舆论。我们利用GPT-3.5-Turbo模型,结合美国全国选举研究、德国纵向选举研究、坐标数据集和中国家庭追踪调查的数据,模拟投票行为和公众舆论。该方法使我们能够考察三种类型的表征偏差:基于国家语言、人口群体和政治体制类型的差异。研究结果显示,模拟性能在投票选择方面普遍优于公众舆论,在英语国家中更为准确,在两党制系统中比多党制系统更有效,在民主环境中比威权体制中更强。这些结果有助于增进我们对计算社会科学领域人工智能应用中偏差的理解,并制定缓解策略。

英文摘要:

This study seeks to identify and quantify biases in simulating political samples with Large Language Models, specifically focusing on vote choice and public opinion. Using the GPT-3.5-Turbo model, we leverage data from the American National Election Studies, German Longitudinal Election Study, Zuobiao Dataset, and China Family Panel Studies to simulate voting behaviors and public opinions. This methodology enables us to examine three types of representation bias: disparities based on the the country's language, demographic groups, and political regime types. The findings reveal that simulation performance is generally better for vote choice than for public opinions, more accurate in English-speaking countries, more effective in bipartisan systems than in multi-partisan systems, and stronger in democratic settings than in authoritarian regimes. These results contribute to enhancing our understanding and developing strategies to mitigate biases in AI applications within the field of computational social science.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑