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

Studies have shown that large pretrained language models exhibit biasesagainst social groups based on race, gender etc, which they inherit from thedatasets they are trained on. Various researchers have proposed mathematicaltools for quantifying and identifying these biases. There have been methodsproposed to mitigate such biases. In this paper, we present a comprehensivequantitative evaluation of different kinds of biases such as race, gender,ethnicity, age etc. exhibited by popular pretrained language models such asBERT, GPT-2 etc. and also present a toolkit that provides plug-and-playinterfaces to connect mathematical tools to identify biases with largepretrained language models such as BERT, GPT-2 etc. and also present users withthe opportunity to test custom models against these metrics. The toolkit alsoallows users to debias existing and custom models using the debiasingtechniques proposed so far. The toolkit is available athttps://github.com/HrishikeshVish/Fairpy.

FairPy: A Toolkit for Evaluation of Social Biases and their Mitigation in Large Language Models