Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?

@inproceedings{laskar2025,
  title     = {Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?},
  author    = {Md Tahmid Rahman Laskar and Mohammed Saidul Islam and Ridwan Mahbub and Ahmed Masry and Mizanur Rahman and Amran Bhuiyan and Mir Tafseer Nayeem and Shafiq Joty and Enamul Hoque and Jimmy Huang},
  booktitle = {ACL 2025 (Industry Track)},
  year      = {2025}
}