@inproceedings{zou-etal-2025-testnuc,
    title = "{T}est{NUC}: Enhancing Test-Time Computing Approaches and Scaling through Neighboring Unlabeled Data Consistency",
    author = "Zou, Henry Peng  and
      Gu, Zhengyao  and
      Zhou, Yue  and
      Chen, Yankai  and
      Zhang, Weizhi  and
      Fang, Liancheng  and
      Wang, Yibo  and
      Li, Yangning  and
      Liu, Kay  and
      Yu, Philip S.",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1486/",
    pages = "30750--30762",
    ISBN = "979-8-89176-251-0",
    abstract = "Test-time computing approaches, which leverage additional computational resources during inference, have been proven effective in enhancing large language model performance. This work introduces a novel, linearly scaling approach, TestNUC, that improves test-time predictions by leveraging the local consistency of neighboring unlabeled data-it classifies an input instance by considering not only the model{'}s prediction on that instance but also on neighboring unlabeled instances. We evaluate TestNUC across eight diverse datasets, spanning intent classification, topic mining, domain discovery, and emotion detection, demonstrating its consistent superiority over baseline methods such as standard prompting and self-consistency. Furthermore, TestNUC can be seamlessly integrated with existing test-time computing approaches, substantially boosting their performance. Our analysis reveals that TestNUC scales effectively with increasing amounts of unlabeled data and performs robustly across different embedding models, making it practical for real-world applications. Our code is available at https://github.com/HenryPengZou/TestNUC."
}