@inproceedings{zhang-etal-2026-identity,
    title = "Identity-Robust Language Model Generation via Content Integrity Preservation",
    author = "Zhang, Miao  and
      Chen, Kelly  and
      Tanjim, Mehrab  and
      Chunara, Rumi",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.884/",
    pages = "19356--19370",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Model (LLM) outputs often vary across user sociodemographic attributes, leading to disparities in factual accuracy, utility, and safety, even for objective questions where demographic information is irrelevant. Unlike prior work on stereotypical or representational bias, this paper studies identity-dependent degradation of core response quality. We show empirically that such degradation arises from biased generation behavior, despite factual knowledge being robustly encoded across identities. Motivated by this mismatch, we propose a lightweight, training-free framework for identity-robust generation that selectively neutralizes non-critical identity information while preserving semantically essential attributes, thus maintaining output content integrity. Experiments across four benchmarks and 18 sociodemographic identities demonstrate an average 66.3{\%} reduction in identity-dependent bias compared to vanilla prompting and outperforms existing prompt-based defenses. Our work addresses a critical gap in mitigating the impact of user identity cues in prompts on core generation quality."
}