@inproceedings{qi-etal-2024-tag,
    title = "Tag-grounded Visual Instruction Tuning with Retrieval Augmentation",
    author = "Qi, Daiqing  and
      Zhao, Handong  and
      Wei, Zijun  and
      Li, Sheng",
    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/fix-sig-urls/2024.emnlp-main.120/",
    doi = "10.18653/v1/2024.emnlp-main.120",
    pages = "2008--2026"
}