A Cautionary Tale About "Neutrally" Informative AI Tools Ahead of the 2025 Federal Elections in Germany
This research highlights critical issues in AI tools for political information, potentially misleading voters in democratic processes, though it is incremental as it builds on existing concerns about bias and reliability in such applications.
The study assessed the reliability of AI-based Voting Advice Applications and large language models in providing objective political information for the 2025 German federal elections, finding significant biases in LLMs favoring left-wing parties and substantial deviations in VAAs from established party positions, with one VAA showing over 50% deviations and susceptibility to hallucinations.
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.