@inproceedings{rudman-etal-2026-mechanisms,
    title = "Mechanisms of Prompt-Induced Hallucination in Vision{--}Language Models",
    author = "Rudman, William  and
      Golovanevsky, Michal  and
      Arad, Dana  and
      Belinkov, Yonatan  and
      Eickhoff, Carsten  and
      Singh, Ritambhara  and
      Mahowald, Kyle",
    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.1941/",
    pages = "41894--41912",
    ISBN = "979-8-89176-390-6",
    abstract = "Large vision{--}language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-counting setting, where the prompt overstates the number of objects in the image (e.g., asking a model to describe \textit{four} waterlilies when only \textit{three} are present). At low object counts, models often correct the overestimation, but as the number of objects increases, they increasingly conform to the prompt regardless of the discrepancy. Through mechanistic analysis of three VLMs, we identify a small set of attention heads whose ablation substantially reduces prompt-induced hallucinations (PIH) by at least 40{\%} without additional training. Across models, PIH-heads mediate prompt copying in model-specific ways. We characterize these differences and show that PIH ablation increases correction toward visual evidence. Our findings offer insights into the internal mechanisms driving prompt-induced hallucinations, revealing model-specific differences in how these behaviors are implemented."
}