@inproceedings{marcuzzi-etal-2026-quantization,
    title = "How Quantization Shapes Bias in Large Language Models",
    author = "Marcuzzi, Federico  and
      Ning, Xuefei  and
      Schwartz, Roy  and
      Gurevych, Iryna",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.17/",
    pages = "363--404",
    ISBN = "979-8-89176-380-7",
    abstract = "This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual demographic subgroups.We focus on weight and activation quantization strategies and examine their effects across a broad range of bias types, including stereotypes, fairness, toxicity, and sentiment.We employ both probability- and generated text-based metrics across 13 benchmarks and evaluate models that differ in architecture family and reasoning ability.Our findings show that quantization has a nuanced impact on bias: while it can reduce model toxicity and does not significantly impact sentiment, it tends to slightly increase stereotypes and unfairness in generative tasks, especially under aggressive compression.These trends are generally consistent across demographic categories and subgroups, and model types, although their magnitude depends on the specific setting.Overall, our results highlight the importance of carefully balancing efficiency and ethical considerations when applying quantization in practice."
}