@inproceedings{thaler-etal-2026-far,
    title = "How Far Can Bias Go? Tracing Bias from Pre-Training Data to Alignment",
    author = {Thaler, Marion  and
      K{\"o}ksal, Abdullatif  and
      Leidinger, Alina  and
      Anna Korhonen, Anna  and
      Sch{\"u}tze, Hinrich},
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2026.lrec-1.315/",
    doi = "10.63317/4zeoky6waeng",
    pages = "3975--3995",
    abstract = "As LLMs are increasingly integrated into user-facing applications, addressing biases that perpetuate societal inequalities is crucial. While much work has gone into measuring and mitigating biases, fewer studies have investigated their origins. Therefore, this study examines the propagation of representational gender-occupation bias from pre-training data to LLM generations. Using zero-shot prompting and token co-occurrence analyses, we explore how biases in the pre-training data influence model generations. Our findings reveal that representational biases present in the pre-training data are amplified in the model generations, regardless of hyperparameters and prompting type. By comparing gender representation in the pre-training data with real-world distributions, our research highlights discrepancies between the data and the model, underscoring the importance of further work in mitigating bias at the data level."
}