@article{hsu-etal-2026-large,
    title = "Do Large Multimodal Models Solve Caption Generation for Scientific Figures? Lessons Learned from {S}ci{C}ap Challenge 2023",
    author = "Hsu, Ting-Yao  and
      Hsu, Yi-Li  and
      Rohatgi, Shaurya  and
      Huang, Chieh-Yang  and
      Ng, Ho Yin Sam  and
      Rossi, Ryan  and
      Kim, Sungchul  and
      Yu, Tong  and
      Ku, Lun-Wei  and
      Giles, Clyde Lee  and
      Huang, Ting-Hao",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "14",
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest-latest-mitpress-cl-tacl/2026.tacl-1.12/",
    doi = "10.1162/tacl.a.653",
    pages = "233--252"
}