基于人物特征的欧洲议会投票行为模拟研究：利用大语言模型
Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models
AI总结：
本研究利用大语言模型和人物提示技术，模拟欧洲议会成员的投票行为，实现约 0.793 的加权 F1 分数。
摘要：
大语言模型（LLMs）在理解和生成政治 discourse 方面表现出显著能力，但被发现普遍存在渐进左倾偏见。同时，所谓的 'personality' 或身份提示已被证明可以产生与基础模型不一致的社会经济群体相一致的 LLM 行为。在本研究中，我们分析零样本人物提示结合有限信息是否能准确预测个体投票决策，并通过聚合准确预测欧洲各群体在多样政策上的立场。我们评估预测在回应反事实论点、不同人物提示和生成方法时的稳定性。最后，我们发现可以合理模拟欧洲议会成员的投票行为，达到约 0.793 的加权 F1 分数。我们的政治人物数据集以及代码可在以下网址获取：https://github.com/dess-mannheim/european_parliament_simulation。
英文摘要：
Large Language Models (LLMs) display remarkable capabilities to understand or even produce political discourse but have been found to consistently exhibit a progressive left-leaning bias. At the same time, so-called persona or identity prompts have been shown to produce LLM behavior that aligns with socioeconomic groups with which the base model is not aligned. In this work, we analyze whether zero-shot persona prompting with limited information can accurately predict individual voting decisions and, by aggregation, accurately predict the positions of European groups on a diverse set of policies. We evaluate whether predictions are stable in response to counterfactual arguments, different persona prompts, and generation methods. Finally, we find that we can simulate the voting behavior of Members of the European Parliament reasonably well, achieving a weighted F1 score of approximately 0.793. Our persona dataset of politicians in the 2024 European Parliament and our code are available at the following url: https://github.com/dess-mannheim/european_parliament_simulation.
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。
