@article{whydollavavisionlanguagemodelsreplyto,
  title = {Why do LLaVA Vision-Language Models Reply to Images in English?},
  author = {Musashi Hinck and Carolin Holtermann and Matthew Lyle Olson and Florian Schneider and Sungduk Yu and Anahita Bhiwandiwalla and Anne Lauscher and ShaoYen Tseng and Vasudev Lal},
  year = {2024},
  eprint = {2407.02333},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.02333v1},
}