@article{overcomingvisionlanguagemodelchallenges,
  title = {Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions},
  author = {Shue Shiinoki and Ryo Koshihara and Hayato Motegi and Masumi Morishige},
  year = {2025},
  eprint = {2502.04389},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.04389v1},
}