你会投票给谁？大型语言模型（LLM）的政治立场审计：意大利案例研究

中文摘要 AI 辅助

随着用户在政治事务（尤其是选举期间）上越来越多地转向大型语言模型（LLM）获取信息和建议，这些系统表达的政治偏好已成为公众关注的问题。先前研究表明，与LLM的交互会影响用户的政治态度和选择，引发了人们对这些模型自身如何评价政治行为体的疑问。在本文中，我们研究LLM是否以及如何表达对政党和政治领导人的偏好。我们引入了一个系统且可复现的审计框架，在该框架中，我们提示多个LLM按照九个标准对政党和领导人进行评价。我们不试图推断模型的“真实”政治信仰，而是聚焦于其可观察的行为，考察评价的一致性、模型之间的差异、弃权（不执行）率以及对提示表述的敏感性。我们还研究了当模型被要求采用不同角色时，这些评价会如何变化。我们通过一项意大利案例研究来展示该框架，对LLM生成的关于意大利政党和领导人的政治评价进行了系统分析。

英文摘要

As users increasingly turn to Large Language Models (LLMs) for information and advice on political matters, particularly during election periods, the political preferences expressed by these systems have become a matter of public interest. Prior research has shown that interactions with LLMs can influence users' political attitudes and choices, raising questions about how these models themselves evaluate political actors. In this paper, we investigate whether and how LLMs express preferences toward political parties and political leaders. We introduce a systematic and reproducible auditing framework in which multiple LLMs are prompted to evaluate parties and leaders across nine criteria. Rather than attempting to infer the models' "true" political beliefs, we focus on their observable behavior, examining consistency across evaluations, differences between models, refusal rates, and sensitivity to prompt formulation. We further investigate how these evaluations vary when models are instructed to adopt different personas. We demonstrate the framework through an Italian case study, providing a systematic analysis of LLM-generated political evaluations on italian parties and leaders.

发表机构

• Revelis s.r.l.（雷维利斯有限责任公司）

机构由 AI 辅助整理，请以论文原文为准。