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

Out-of-distribution (OOD) detection aims to discern outliers from theintended data distribution, which is crucial to maintaining high reliabilityand a good user experience. Most recent studies in OOD detection utilize theinformation from a single representation that resides in the penultimate layerto determine whether the input is anomalous or not. Although such a method isstraightforward, the potential of diverse information in the intermediatelayers is overlooked. In this paper, we propose a novel framework based oncontrastive learning that encourages intermediate features to learnlayer-specialized representations and assembles them implicitly into a singlerepresentation to absorb rich information in the pre-trained language model.Extensive experiments in various intent classification and OOD datasetsdemonstrate that our approach is significantly more effective than other works.

Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble