English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pre-trained language models (PLMs) have exhibited remarkable few-shotlearning capabilities when provided a few examples in a natural language promptas demonstrations of test instances, i.e., in-context learning. However, theperformance of in-context learning is susceptible to the choice of promptformat, training examples and the ordering of the training examples. In thispaper, we propose a novel nearest-neighbor calibration framework for in-contextlearning to ease this issue. It is inspired by a phenomenon that the in-contextlearning paradigm produces incorrect labels when inferring training instances,which provides a useful supervised signal to calibrate predictions. Thus, ourmethod directly augments the predictions with a $k$-nearest-neighbor ($k$NN)classifier over a datastore of cached few-shot instance representationsobtained by PLMs and their corresponding labels. Then adaptive neighborselection and feature regularization modules are introduced to make full use ofa few support instances to reduce the $k$NN retrieval noise. Experiments onvarious few-shot text classification tasks demonstrate that our methodsignificantly improves in-context learning, while even achieving comparableperformance with state-of-the-art tuning-based approaches in some sentimentanalysis tasks.

Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration