@inproceedings{hinck-etal-2024-llava,
    title = "Why do {LL}a{VA} Vision-Language Models Reply to Images in {E}nglish?",
    author = "Hinck, Musashi  and
      Holtermann, Carolin  and
      Olson, Matthew Lyle  and
      Schneider, Florian  and
      Yu, Sungduk  and
      Bhiwandiwalla, Anahita  and
      Lauscher, Anne  and
      Tseng, Shao-Yen  and
      Lal, Vasudev",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2024.findings-emnlp.783/",
    doi = "10.18653/v1/2024.findings-emnlp.783",
    pages = "13402--13421"
}