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

The Stereotype Content model (SCM) states that we tend to perceive minoritygroups as cold, incompetent or both. In this paper we adapt existing work todemonstrate that the Stereotype Content model holds for contextualised wordembeddings, then use these results to evaluate a fine-tuning process designedto drive a language model away from stereotyped portrayals of minority groups.We find the SCM terms are better able to capture bias than demographic agnosticterms related to pleasantness. Further, we were able to reduce the presence ofstereotypes in the model through a simple fine-tuning procedure that requiredminimal human and computer resources, without harming downstream performance.We present this work as a prototype of a debiasing procedure that aims toremove the need for a priori knowledge of the specifics of bias in the model.

A Robust Bias Mitigation Procedure Based on the Stereotype Content Model