@inproceedings{fanton-etal-2025-diachronic,
    title = "A Diachronic Analysis of Human and Model Predictions on Audience Gender in How-to Guides",
    author = "Fanton, Nicola  and
      Ranjan, Sidharth  and
      Malsburg, Titus Von Der  and
      Roth, Michael",
    editor = "Fale{\'n}ska, Agnieszka  and
      Basta, Christine  and
      Costa-juss{\`a}, Marta  and
      Sta{\'n}czak, Karolina  and
      Nozza, Debora",
    booktitle = "Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.gebnlp-1.22/",
    doi = "10.18653/v1/2025.gebnlp-1.22",
    pages = "242--255",
    ISBN = "979-8-89176-277-0",
    abstract = "We examine audience-specific how-to guides on wikiHow, in English, diachronically by comparing predictions from fine-tuned language models and human judgments. Using both early and revised versions, we quantitatively and qualitatively study how gender-specific features are identified over time. While language model performance remains relatively stable in terms of macro F$_1$-scores, we observe an increased reliance on stereotypical tokens. Notably, both models and human raters tend to overpredict women as an audience, raising questions about bias in the evaluation of educational systems and resources."
}