@article{morethanthefinalanswerimprovingvisualext,
  title = {More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models},
  author = {Hoang Anh Just and Yifei Fan and Handong Zhao and Jiuxiang Gu and Ruiyi Zhang and Simon Jenni and Kushal Kafle and Ruoxi Jia and Jing Shi},
  year = {2025},
  eprint = {2512.12487},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.12487},
}