@inproceedings{liu-etal-2025-learning-llm,
    title = "Learning {LLM} Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings",
    author = "Liu, Xuanqing  and
      Kong, Luyang  and
      Niu, Wei  and
      Khashei, Afshin  and
      Zeng, Belinda  and
      Johnson, Steve  and
      Jay, Jon  and
      Golac, Davor  and
      Pope, Matt",
    editor = "Chen, Weizhu  and
      Yang, Yi  and
      Kachuee, Mohammad  and
      Fu, Xue-Yong",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-industry.8/",
    pages = "86--98",
    ISBN = "979-8-89176-194-0",
    abstract = "Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing systems, making it impractical to deploy models with billions of parameters due to latency constraints. As a result, practitioners often prefer smaller models with millions of parameters, trained on high-quality, human-annotated datasets. Yet, curating such datasets is both time-consuming and costly. Consequently, there is a growing need to combine the scalability of LLM-generated labels with the precision of human annotations, enabling fine-tuned smaller models to achieve both higher speed and accuracy comparable to larger models. In this paper, we introduce a simple yet effective framework to address this challenge. Our approach is specifically designed for per-utterance classification problems, which encompass tasks such as intent detection, dialogue state tracking, and more. To mitigate the impact of labeling errors from LLMs {--} the primary source of inaccuracies in student models {--} we propose a noise-reduced preference learning loss. Experimental results demonstrate that our method significantly improves accuracy across utterance-level dialogue tasks, including sentiment detection (over 2{\%}), dialogue act classification (over 1.5{\%}), etc."
}