@inproceedings{kononykhina-etal-2025-mind,
    title = "Mind the Gap: Gender-based Differences in Occupational Embeddings",
    author = "Kononykhina, Olga  and
      Haensch, Anna-Carolina  and
      Kreuter, Frauke",
    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-1.7/",
    doi = "10.18653/v1/2025.gebnlp-1.7",
    pages = "83--91",
    ISBN = "979-8-89176-277-0",
    abstract = "Large Language Models (LLMs) offer promising alternatives to traditional occupational coding approaches in survey research. Using a German dataset, we examine the extent to which LLM-based occupational coding differs by gender. Our findings reveal systematic disparities: gendered job titles (e.g., ``Autor'' vs. ``Autorin'', meaning ``male author'' vs. ``female author'') frequently result in diverging occupation codes, even when semantically identical. Across all models, 54{\%}{--}82{\%} of gendered inputs obtain different Top-5 suggestions. The practical impact, however, depends on the model. GPT includes the correct code most often (62{\%}) but demonstrates female bias (up to +18 pp). IBM is less accurate (51{\%}) but largely balanced. Alibaba, Gemini, and MiniLM achieve about 50{\%} correct-code inclusion, and their small ({\ensuremath{<}} 10 pp) and direction-flipping gaps could indicate a sampling noise rather than gender bias. We discuss these findings in the context of fairness and reproducibility in NLP applications for social data."
}