@inproceedings{jian-etal-2024-large,
    title = "Large Language Models Know What is Key Visual Entity: An {LLM}-assisted Multimodal Retrieval for {VQA}",
    author = "Jian, Pu  and
      Yu, Donglei  and
      Zhang, Jiajun",
    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.613/",
    doi = "10.18653/v1/2024.emnlp-main.613",
    pages = "10939--10956"
}