kNN-Prompt: Nearest Neighbor Zero-Shot Inference. (arXiv:2205.13792v2 [cs.CL] UPDATED)

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 …

arxiv inference knn