@inproceedings{zhang-etal-2025-pairwise,
    title = "Pairwise Prompt-Based Tuning with Parameter Efficient Fast Adaptation for Generalized Zero-Shot Intent Detection",
    author = "Zhang, Xiaotong  and
      Zhou, Qianru  and
      Liu, Han  and
      Yu, Hong",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2025.findings-naacl.52/",
    pages = "917--929",
    ISBN = "979-8-89176-195-7",
    abstract = "Generalized zero-shot intent detection (GZID) aims to recognize the labels of utterances from both seen and unseen intents by utilizing the knowledge learned from seen intents. Enhancing the generalization ability from seen intents to unseen intents is a key challenge in the GZID setting. Existing methods attempt to tackle this challenge by distinguishing unseen intents from seen intents or focusing on enhancing the model discriminability. However, the challenge is not solved substantially as they ignore to promote the representation learning ability of the model itself and neglect to strengthen the model adaptability to new tasks, resulting in overfitting on the seen intents. In this paper, we propose a pairwise prompt-based tuning model with parameter efficient fast adaptation which involves two training steps. In the first step, we leverage hybrid contrastive learning in discriminant space and masked language modeling to make predictions at both sentence and token levels, which can enhance the model discriminability and representation learning ability respectively. In the second step, we design a pipeline for generating and filtering unseen data by only providing unseen intent labels, and utilize parameter-efficient fine-tuning to quickly adapt to unseen intents. Experiments on four intent detection datasets demonstrate that our two-step training method has better comprehension and generalization capabilities."
}