@inproceedings{gan-etal-2026-textual,
    title = "Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models",
    author = "Gan, Woody Haosheng  and
      Fu, Deqing  and
      Asilis, Julian  and
      Liu, Ollie  and
      Sharan, Vatsal  and
      Jia, Robin  and
      Neiswanger, Willie",
    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.1861/",
    pages = "40056--40087",
    ISBN = "979-8-89176-390-6",
    abstract = "Steering methods have emerged as effective tools for guiding large language models' behavior, yet multimodal large language models (MLLMs) lack comparable techniques due to architectural diversity and limited availability of multimodal steering vectors. Inspired by this gap, we demonstrate that steering vectors derived solely from text-only LLM backbones can effectively guide and enhance their multimodal counterparts, revealing a novel cross-modal transfer that enables reuse of existing interpretability tools. Using community-standard methods{---}Sparse Autoencoders (SAE), Mean Shift, and Linear Probing{---}we validate this transfer effect across diverse MLLM architectures and visual reasoning tasks. Text-derived steering consistently enhances multimodal performance, with Mean Shift achieving up to +7.3{\%} improvement in spatial relationship accuracy and +3.3{\%} in counting accuracy on CV-Bench, and exhibits strong generalization to out-of-distribution datasets, for example reaching +34.2{\%} on CLEVR counting tasks. This reveals that textual representations alone can effectively enhance visual grounding in MLLMs, bridging the mature ecosystem of text-based steering to MLLMs with minimal additional data collection or computational overhead."
}