@inproceedings{malik-etal-2026-ask,
    title = "Ask Me Again Differently: {GRAS} for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone",
    author = "Malik, Shaivi  and
      Abdullah, Hasnat Md  and
      Saha, Sriparna  and
      Sheth, Amit",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.123/",
    pages = "2327--2388",
    ISBN = "979-8-89176-386-9",
    abstract = "As Vision Language Models (VLMs) become integral to real-world applications, understanding their demographic biases is critical. We introduce GRAS, a benchmark for uncovering demographic biases in VLMs across gender, race, age, and skin tone, offering the most diverse coverage to date. We further propose the GRAS Bias Score, an interpretable metric for quantifying bias. We benchmark five state-of-the-art VLMs and reveal concerning bias levels, with the least biased model attaining a GRAS Bias Score of 98, far from the unbiased ideal of 0. Our findings also reveal a methodological insight: evaluating bias in VLMs with visual question answering (VQA) requires considering multiple formulations of a question. Our code, data, and evaluation results are publicly available at https://github.com/shaivimalik/gras{\_}bias{\_}bench"
}