@article{whenandwhyvisionlanguagemodelsbehave,
  title = {When and why vision-language models behave like bags-of-words, and what to do about it?},
  author = {Mert Yuksekgonul and Federico Bianchi and Pratyusha Kalluri and Dan Jurafsky and James Zou},
  year = {2022},
  eprint = {2210.01936},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.01936v3},
}