测试德国选举期AI工具，发现多数存在政治偏见且易被误导
A Cautionary Tale About "Neutrally" Informative AI Tools Ahead of the 2025 Federal Elections in Germany
- 对比选民指南与政党立场，检测AI推荐偏差
- 大模型对左翼支持超75%，右翼仅约30%
- 部分投票建议工具偏离真实立场超50%，可被恶意诱导
本研究评估基于AI的投票建议应用（VAAs）和大语言模型（LLMs）在提供客观政治信息方面的可靠性。分析依据是与德国成熟的在线工具Wahl-O-Mat中38项陈述的政党立场进行对比。结果显示，LLMs表现出显著偏见：平均对左翼政党认同度超过75%，对中间偏右政党认同度低于50%，对右翼政党认同度约为30%。对于本应客观的VAAs，我们发现明显偏离：一个工具在25%情况下出现偏差，另一个则超过50%。更严重的是，后者在简单提示注入后产生严重幻觉，甚至虚构出政党与右翼极端主义的不存在关联。
原文摘要 · Abstract (English)
In this study, we examine the reliability of AI-based Voting Advice Applications (VAAs) and large language models (LLMs) in providing objective political information. Our analysis is based upon a comparison with party responses to 38 statements of the Wahl-O-Mat, a well-established German online tool that helps inform voters by comparing their views with political party positions. For the LLMs, we identify significant biases. They exhibit a strong alignment (over 75% on average) with left-wing parties and a substantially lower alignment with center-right (smaller 50%) and right-wing parties (around 30%). Furthermore, for the VAAs, intended to objectively inform voters, we found substantial deviations from the parties' stated positions in Wahl-O-Mat: While one VAA deviated in 25% of cases, another VAA showed deviations in more than 50% of cases. For the latter, we even observed that simple prompt injections led to severe hallucinations, including false claims such as non-existent connections between political parties and right-wing extremist ties.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。