@article{dolargemultimodalmodelssolvecaption,
  title = {Do Large Multimodal Models Solve Caption Generation for Scientific Figures? Lessons Learned from SCICAP Challenge 2023},
  author = {Ting-Yao E. Hsu and Yi-Li Hsu and Shaurya Rohatgi and Chieh-Yang Huang and Ho Yin Sam Ng and Ryan Rossi and Sungchul Kim and Tong Yu and Lun-Wei Ku and C. Lee Giles and Ting-Hao K. Huang},
  year = {2025},
  eprint = {2501.19353},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.19353v1},
}