@inproceedings{zhao-etal-2025-multimodal,
    title = "Are Multimodal {LLM}s Robust Against Adversarial Perturbations? {R}o{MM}ath: A Systematic Evaluation on Multimodal Math Reasoning",
    author = "Zhao, Yilun  and
      Gan, Guo  and
      Zhao, Chen  and
      Cohan, Arman",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.naacl-long.582/",
    pages = "11653--11665",
    ISBN = "979-8-89176-189-6",
    abstract = "We introduce RoMMath, the first benchmark designed to evaluate the capabilities and robustness of multimodal large language models (MLLMs) in handling multimodal math reasoning, particularly when faced with adversarial perturbations. RoMMath consists of 4,800 expert-annotated examples, including an original set and seven adversarial sets, each targeting a specific type of perturbation at the text or vision levels. We evaluate a broad spectrum of 17 MLLMs on RoMMath and uncover a critical challenge regarding model robustness against adversarial perturbations. Through detailed error analysis by human experts, we gain a deeper understanding of the current limitations of MLLMs. Additionally, we explore various approaches to enhance the performance and robustness of MLLMs, providing insights that can guide future research efforts."
}