@inproceedings{lee-etal-2025-saferoute,
    title = "{S}afe{R}oute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models",
    author = "Lee, Seanie  and
      Lee, Dong Bok  and
      Wagner, Dominik  and
      Kang, Minki  and
      Seong, Haebin  and
      Bocklet, Tobias  and
      Lee, Juho  and
      Hwang, Sung Ju",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.findings-acl.105/",
    pages = "2053--2069",
    ISBN = "979-8-89176-256-5",
    abstract = "Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achieve strong performance, their computational cost is substantial. To mitigate this, smaller distilled models are used, but they often underperform on ``hard'' examples where the larger model provides accurate predictions. We observe that many inputs can be reliably handled by the smaller model, while only a small fraction require the larger model{'}s capacity. Motivated by this, we propose SafeRoute, a binary router that distinguishes hard examples from easy ones. Our method selectively applies the larger safety guard model to the data that the router considers hard, improving efficiency while maintaining accuracy compared to solely using the larger safety guard model. Experimental results on multiple benchmark datasets demonstrate that our adaptive model selection significantly enhances the trade-off between computational cost and safety performance, outperforming relevant baselines."
}