@inproceedings{farinhas-etal-2025-translate,
    title = "Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral",
    author = "Farinhas, Ant{\'o}nio  and
      Guerreiro, Nuno M  and
      Agrawal, Sweta  and
      Rei, Ricardo  and
      Martins, Andre",
    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.1358/",
    pages = "26730--26744",
    ISBN = "979-8-89176-332-6",
    abstract = "Larger models often outperform smaller ones but come with high computational costs. Cascading offers a potential solution. By default, it uses smaller models and defers only some instances to larger, more powerful models. However, designing effective deferral rules remains a challenge. In this paper, we propose a simple yet effective approach for machine translation, using existing quality estimation (QE) metrics as deferral rules. We show that QE-based deferral allows a cascaded system to match the performance of a larger model while invoking it for a small fraction (30{\%} to 50{\%}) of the examples, significantly reducing computational costs. We validate this approach through both automatic and human evaluation."
}