@inproceedings{shi-etal-2026-msvbench, title = "{MSVB}ench: Towards Human-Level Evaluation of Multi-Shot Video Generation", author = "Shi, Haoyuan and li, Yunxin and Deng, Nanhao and Xu, Zhenran and Chen, Xinyu and Wang, Longyue and Hu, Baotian and Zhang, Min", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1203/", pages = "24034--24058", ISBN = "979-8-89176-395-1" }