Papers › kNN-Prompt: Nearest Neighbor Zero-Shot Inference

kNN-Prompt: Nearest Neighbor Zero-Shot Inference

27 May 2022arXiv:2205.13792archive 2025-07-28

Weijia Shi, Julian Michael, Suchin Gururangan, Luke Zettlemoyer

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.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

swj0419/knn_prompt officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain Adaptation Language Modelling Open-Ended Question Answering Question Answering Retrieval Sentiment Analysis Sentiment Classification Text Classification text-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BASE BPE Cosine Annealing Dense Connections Discriminative Fine-Tuning Dropout GPT-2 Layer Normalization Linear Layer Linear Warmup With Cosine Annealing Multi-Head Attention Residual Connection Softmax Weight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections