English

kNN-Prompt: Nearest Neighbor Zero-Shot Inference

Computation and Language 2022-11-03 v2

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 zero-shot 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.

Keywords

Cite

@article{arxiv.2205.13792,
  title  = {kNN-Prompt: Nearest Neighbor Zero-Shot Inference},
  author = {Weijia Shi and Julian Michael and Suchin Gururangan and Luke Zettlemoyer},
  journal= {arXiv preprint arXiv:2205.13792},
  year   = {2022}
}
R2 v1 2026-06-24T11:30:34.068Z