@inproceedings{yang-etal-2025-audio-centric, title = "Audio-centric Video Understanding Benchmark without Text Shortcut", author = "Yang, Yudong and Zhuang, Jimin and Sun, Guangzhi and Tang, Changli and Li, Yixuan and Li, Peihan and Jiang, Yifan and Li, Wei and Ma, Zejun and Zhang, Chao", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.333/", pages = "6580--6598", ISBN = "979-8-89176-332-6" }