@inproceedings{jakob-etal-2025-polbix,
    title = "{P}ol{B}i{X}: Detecting {LLM}s' Political Bias in Fact-Checking through {X}-phemisms",
    author = "Jakob, Charlott  and
      Harbecke, David  and
      Parschan, Patrick  and
      Neves, Pia Wenzel  and
      Schmitt, Vera",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.932/",
    doi = "10.18653/v1/2025.findings-emnlp.932",
    pages = "17192--17210",
    ISBN = "979-8-89176-335-7",
    abstract = "Large Language Models are increasingly used in applications requiring objective assessment, which could be compromised by political bias. Many studies found preferences for left-leaning positions in LLMs, but downstream effects on tasks like fact-checking remain underexplored. In this study, we systematically investigate political bias through exchanging words with euphemisms or dysphemisms in German claims. We construct minimal pairs of factually equivalent claims that differ in political connotation, to assess the consistency of LLMs in classifying them as true or false. We evaluate six LLMs and find that, more than political leaning, the presence of judgmental words significantly influences truthfulness assessment. While a few models show tendencies of political bias, this is not mitigated by explicitly calling for objectivism in prompts. Warning: This paper contains content that may be offensive or upsetting."
}