@article{understandingmultimodalllmsthemechanisti,
  title = {Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering},
  author = {Zeping Yu and Sophia Ananiadou},
  year = {2024},
  eprint = {2411.10950},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.10950v2},
}