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

Numerous debiasing techniques have been proposed to mitigate the gender biasthat is prevalent in pretrained language models. These are often evaluated ondatasets that check the extent to which the model is gender-neutral in itspredictions. Importantly, this evaluation protocol overlooks the possibleadverse impact of bias mitigation on useful gender knowledge. To fill this gap,we propose DiFair, a manually curated dataset based on masked language modelingobjectives. DiFair allows us to introduce a unified metric, gender invariancescore, that not only quantifies a model's biased behavior, but also checks ifuseful gender knowledge is preserved. We use DiFair as a benchmark for a numberof widely-used pretained language models and debiasing techniques. Experimentalresults corroborate previous findings on the existing gender biases, while alsodemonstrating that although debiasing techniques ameliorate the issue of genderbias, this improvement usually comes at the price of lowering useful genderknowledge of the model.

DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Bias