@inproceedings{shin-etal-2026-relations,
    title = "When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise",
    author = "Shin, Philip Wootaek  and
      Sridhar, Ajay Narayanan  and
      Devarapalli, Lakshmi Sivani  and
      Zhang, Rui  and
      Sampson, Jack  and
      Narayanan, Vijaykrishnan",
    editor = "Yan, Qianqi  and
      Montariol, Syrielle  and
      Fan, Yue  and
      Gu, Jing  and
      Pan, Jiayi  and
      Li, Manling  and
      Kordjamshidi, Parisa  and
      Suhr, Alane  and
      Wang, Xin Eric",
    booktitle = "Proceedings of the 4th Workshop on Advances in Language and Vision Research ({ALVR})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.alvr-main.14/",
    pages = "180--185",
    ISBN = "979-8-89176-398-2",
    abstract = "Vision{--}language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over inter-object interactions. We study the impact of visual perturbations, specifically rotation and noise, and show that even mild distortions significantly degrade relational reasoning across models and datasets. We further evaluate prompt-based augmentation and preprocessing strategies (orientation correction and denoising), finding that while they offer partial improvements, they do not fully resolve hallucinations. Our results reveal a gap between perceptual robustness and relational understanding, highlighting the need for more robust, geometry-aware VLMs."
}