@inproceedings{wessel-2025-llm,
    title = "{LLM}-based Adversarial Dataset Augmentation for Automatic Media Bias Detection",
    author = "Wessel, Martin",
    editor = "Kazantseva, Anna  and
      Szpakowicz, Stan  and
      Degaetano-Ortlieb, Stefania  and
      Bizzoni, Yuri  and
      Pagel, Janis",
    booktitle = "Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.latechclfl-1.3/",
    pages = "19--24",
    ISBN = "979-8-89176-241-1",
    abstract = "This study presents BiasAdapt, a novel data augmentation strategy designed to enhance the robustness of automatic media bias detection models. Leveraging the BABE dataset, BiasAdapt uses a generative language model to identify bias-indicative keywords and replace them with alternatives from opposing categories, thus creating adversarial examples that preserve the original bias labels. The contributions of this work are twofold: it proposes a scalable method for augmenting bias datasets with adversarial examples while preserving labels, and it publicly releases an augmented adversarial media bias dataset.Training on BiasAdapt reduces the reliance on spurious cues in four of the six evaluated media bias categories."
}