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

Prompt-based classification adapts tasks to a cloze question format utilizingthe [MASK] token and the filled tokens are then mapped to labels throughpre-defined verbalizers. Recent studies have explored the use of verbalizerembeddings to reduce labor in this process. However, all existing studiesrequire a tuning process for either the pre-trained models or additionaltrainable embeddings. Meanwhile, the distance between high-dimensionalverbalizer embeddings should not be measured by Euclidean distance due to thepotential for non-linear manifolds in the representation space. In this study,we propose a tuning-free manifold-based space re-embedding method calledLocally Linear Embedding with Intra-class Neighborhood Constraint (LLE-INC) forverbalizer embeddings, which preserves local properties within the same classas guidance for classification. Experimental results indicate that even withouttuning any parameters, our LLE-INC is on par with automated verbalizers withparameter tuning. And with the parameter updating, our approach furtherenhances prompt-based tuning by up to 3.2%. Furthermore, experiments with theLLaMA-7B&13B indicate that LLE-INC is an efficient tuning-free classificationapproach for the hyper-scale language models.

Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification