@article{canpretrainedvisionandlanguagemodels,
  title = {Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?},
  author = {Yang Chen and Hexiang Hu and Yi Luan and Haitian Sun and Soravit Changpinyo and Alan Ritter and Ming-Wei Chang},
  year = {2023},
  eprint = {2302.11713},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.11713v5},
}