A Cautionary Tale About "Neutrally" Informative AI Tools Ahead of the 2025 Federal Elections in Germany

TL;DR

This paper critically examines the reliability of AI tools like VAAs and LLMs in providing objective political information during the 2025 German elections, revealing significant biases and inaccuracies that could mislead voters.

Contribution

It provides a comparative analysis of AI-based VAAs and LLMs against established political tools, highlighting biases and hallucinations that compromise their objectivity.

Findings

LLMs show over 75% alignment with left-wing parties

VAAs deviate from party positions in up to 50% of cases

Simple prompt injections can cause severe hallucinations in VAAs

Abstract

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.