@inproceedings{peng-etal-2025-firewall,
    title = "Firewall Routing: Blocking Leads to Better Hybrid Inference for {LLM}s",
    author = "Peng, Runyu  and
      Zhou, Yunhua  and
      Lv, Kai  and
      Gao, Yang  and
      Guo, Qipeng  and
      Qiu, Xipeng",
    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.331/",
    pages = "6540--6565",
    ISBN = "979-8-89176-332-6"
}