@inproceedings{dutta-2026-measuring,
    title = "Measuring and Mitigating Racial Bias in Embedding Models: A Comparative Study for Law Enforcement Retrieval",
    author = "Dutta, Archan",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.144/",
    pages = "2160--2167",
    ISBN = "979-8-89176-394-4",
    abstract = "Embedding models are often used for semantic retrieval in high-stakes domains such as law enforcement, where biased outputs can have severe consequences. We systematically measure racial bias in six widely used embedding models by computing similarity scores between crime incident texts that include racial identity tokens and simple law enforcement queries. The analysis reveals that racial descriptors consistently affect cosine similarity scores and retrieval rankings for semantically identical crime incidents. All models exhibit statistically significant bias, with magnitude varying across models. This study provides a comprehensive methodology and metrics to aid the selection of embedding models when deploying NLP-based systems in the law enforcement domain. Organizations can reduce bias at low cost through informed model selection. The methodology establishes reproducible metrics for measuring bias in embedding-based systems."
}