@inproceedings{pottanigari-etal-2026-text,
    title = "Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document {QA}",
    author = "Pottanigari, Nikhil Reddy  and
      Kharaghani, Sepideh  and
      Vadacchino, Saverio  and
      Posada, Alejandro  and
      MacDonald, Kurt  and
      Zhang, Ying",
    editor = "T.Y.S.S., Santosh  and
      Agarwal, Amit  and
      Gupta, Vivek  and
      Kementchedjhieva, Yova  and
      Garimella, Aparna  and
      Hou, Yufang",
    booktitle = "The Proceedings of Workshop on Document Intelligence and Understanding",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.docinsights-1.4/",
    pages = "46--62",
    ISBN = "979-8-89176-477-4"
}