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 derive substantial linguistic and factualknowledge from the massive corpora on which they are trained, and promptengineering seeks to align these models to specific tasks. Unfortunately,existing prompt engineering methods require significant amounts of labeleddata, access to model parameters, or both. We introduce a new method forselecting prompt templates \textit{without labeled examples} and\textit{without direct access to the model}. Specifically, over a set ofcandidate templates, we choose the template that maximizes the mutualinformation between the input and the corresponding model output. Across 8datasets representing 7 distinct NLP tasks, we show that when a template hashigh mutual information, it also has high accuracy on the task. On the largestmodel, selecting prompts with our method gets 90\% of the way from the averageprompt accuracy to the best prompt accuracy and requires no ground truthlabels.

An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels