@inproceedings{xu-etal-2026-generation, title = "Generation-Gated Cascaded Routing for Large Language Models", author = "Xu, Yanqiu and Luo, Han and Feng, Lei", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.2071/", pages = "47162--47181", ISBN = "979-8-89176-459-0" }