@inproceedings{shi-etal-2022-nearest,
    title = "Nearest Neighbor Zero-Shot Inference",
    author = "Shi, Weijia  and
      Michael, Julian  and
      Gururangan, Suchin  and
      Zettlemoyer, Luke",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.emnlp-main.214/",
    doi = "10.18653/v1/2022.emnlp-main.214",
    pages = "3254--3265",
    abstract = "Retrieval-augmented language models (LMs) use non-parametric memory to substantially outperform their non-retrieval counterparts on perplexity-based evaluations, but it is an open question whether they achieve similar gains in few- and zero-shot end-task accuracy. We extensively study one such model, the k-nearest neighbor LM (kNN-LM), showing that the gains marginally transfer. The main challenge is to achieve coverage of the verbalizer tokens that define the different end-task class labels. To address this challenge, we also introduce kNN-Prompt, a simple and effective kNN-LM with automatically expanded fuzzy verbalizers (e.g. to expand ``terrible'' to also include ``silly'' and other task-specific synonyms for sentiment classification). Across nine diverse end-tasks, using kNN-Prompt with GPT-2 large yields significant performance boosts over strong zeroshot baselines (13.4{\%} absolute improvement over the base LM on average). We also show that other advantages of non-parametric augmentation hold for end tasks; kNN-Prompt is effective for domain adaptation with no further training, and gains increase with the size of the retrieval model."
}