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

Large Language Models (LLMs) have shown significant promise in variousapplications, including zero-shot and few-shot learning. However, theirperformance can be hampered by inherent biases. Instead of traditionally soughtmethods that aim to minimize or correct these biases, this study introduces anovel methodology named ``bias-kNN''. This approach capitalizes on the biasedoutputs, harnessing them as primary features for kNN and supplementing withgold labels. Our comprehensive evaluations, spanning diverse domain textclassification datasets and different GPT-2 model sizes, indicate theadaptability and efficacy of the ``bias-kNN'' method. Remarkably, this approachnot only outperforms conventional in-context learning in few-shot scenarios butalso demonstrates robustness across a spectrum of samples, templates andverbalizers. This study, therefore, presents a unique perspective on harnessingbiases, transforming them into assets for enhanced model performance.

Leveraging Biases in Large Language Models: "bias-kNN'' for Effective Few-Shot Learning