@inproceedings{niu-etal-2025-bias,
    title = "Bias and Reliability in {AI} Safety Assessment: Multi-Facet Rasch Analysis of Human Moderators",
    author = "Niu, Chunling  and
      Bradley, Kelly  and
      Ma, Biao  and
      Waltman, Brian  and
      Cossette, Loren  and
      Jin, Rui",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers",
    month = oct,
    year = "2025",
    address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.aimecon-main.42/",
    pages = "393--397",
    ISBN = "979-8-218-84228-4",
    abstract = "Using Multi-Facet Rasch Modeling on 36,400 safety ratings of AI-generated conversations, we reveal significant racial disparities (Asian 39.1{\%}, White 28.7{\%} detection rates) and content-specific bias patterns. Simulations show that diverse teams of 8-10 members achieve 70{\%}+ reliability versus 62{\%} for smaller homogeneous teams, providing evidence-based guidelines for AI-generated content moderation."
}