@article{comtanovelbenchmarkforchainofmulti,
  title = {CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models},
  author = {Zihui Cheng and Qiguang Chen and Jin Zhang and Hao Fei and Xiaocheng Feng and Wanxiang Che and Min Li and Libo Qin},
  year = {2024},
  eprint = {2412.12932},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.12932v1},
}