@inproceedings{jian-etal-2022-contrastive,
    title = "Contrastive Learning for Prompt-based Few-shot Language Learners",
    author = "Jian, Yiren  and
      Gao, Chongyang  and
      Vosoughi, Soroush",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.naacl-main.408/",
    doi = "10.18653/v1/2022.naacl-main.408",
    pages = "5577--5587",
    abstract = "The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive learning framework that clusters inputs from the same class for better generality of models trained with only limited examples. Specifically, we propose a supervised contrastive framework that clusters inputs from the same class under different augmented {\textquotedblleft}views{\textquotedblright} and repel the ones from different classes. We create different {\textquotedblleft}views{\textquotedblright} of an example by appending it with different language prompts and contextual demonstrations. Combining a contrastive loss with the standard masked language modeling (MLM) loss in prompt-based few-shot learners, the experimental results show that our method can improve over the state-of-the-art methods in a diverse set of 15 language tasks. Our framework makes minimal assumptions on the task or the base model, and can be applied to many recent methods with little modification."
}