@inproceedings{sun-etal-2024-surf,
    title = "{SUR}f: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information",
    author = "Sun, Jiashuo  and
      Zhang, Jihai  and
      Zhou, Yucheng  and
      Su, Zhaochen  and
      Qu, Xiaoye  and
      Cheng, Yu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.emnlp-main.434/",
    doi = "10.18653/v1/2024.emnlp-main.434",
    pages = "7611--7629"
}