@inproceedings{esfandiarpoor-etal-2024-clip,
    title = "If {CLIP} Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions",
    author = "Esfandiarpoor, Reza  and
      Menghini, Cristina  and
      Bach, Stephen",
    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/jlcl-multiple-ingestion/2024.emnlp-main.547/",
    doi = "10.18653/v1/2024.emnlp-main.547",
    pages = "9797--9819"
}