@inproceedings{chen-etal-2023-pre-trained,
    title = "Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?",
    author = "Chen, Yang  and
      Hu, Hexiang  and
      Luan, Yi  and
      Sun, Haitian  and
      Changpinyo, Soravit  and
      Ritter, Alan  and
      Chang, Ming-Wei",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-main.925/",
    doi = "10.18653/v1/2023.emnlp-main.925",
    pages = "14948--14968"
}