@article{mdocsumdolvlmsgenuinelycomprehend,
  title = {M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?},
  author = {Haolong Yan and Kaijun Tan and Yeqing Shen and Xin Huang and Zheng Ge and Xiangyu Zhang and Si Li and Daxin Jiang},
  year = {2025},
  eprint = {2503.21839},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.21839v1},
}