@inproceedings{golovanevsky-etal-2025-vlms,
    title = "What Do {VLM}s {NOTICE}? A Mechanistic Interpretability Pipeline for {G}aussian-Noise-free Text-Image Corruption and Evaluation",
    author = "Golovanevsky, Michal  and
      Rudman, William  and
      Palit, Vedant  and
      Eickhoff, Carsten  and
      Singh, Ritambhara",
    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/fix-sig-urls/2025.naacl-long.571/",
    pages = "11462--11482",
    ISBN = "979-8-89176-189-6",
    abstract = "Vision-Language Models (VLMs) have gained prominence due to their success in solving complex cross-modal tasks. However, the internal mechanisms of VLMs, particularly the roles of cross-attention and self-attention in multimodal integration, are not fully understood. To address this gap, we introduce NOTICE, a Gaussian-Noise-free Text-Image Corruption and Evaluation pipeline for mechanistic interpretability in VLMs. NOTICE introduces Semantic Image Pairs (SIP) corruption, the first visual counterpart to Symmetric Token Replacement (STR) for text. Through NOTICE, we uncover a set of ``universal attention heads'' in BLIP and LLaVA that consistently contribute across different tasks and modalities. In BLIP, cross-attention heads implement object detection, object suppression, and outlier suppression, whereas important self-attention heads in LLaVA only perform outlier suppression. Notably, our findings reveal that cross-attention heads perform image-grounding, while self-attention in LLaVA heads do not, highlighting key differences in how VLM architectures handle multimodal learning."
}