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 capabilities of natural language models trained on large-scale data haveincreased immensely over the past few years. Open source libraries such asHuggingFace have made these models easily available and accessible. While priorresearch has identified biases in large language models, this paper considersbiases contained in the most popular versions of these models when applied`out-of-the-box' for downstream tasks. We focus on generative language modelsas they are well-suited for extracting biases inherited from training data.Specifically, we conduct an in-depth analysis of GPT-2, which is the mostdownloaded text generation model on HuggingFace, with over half a milliondownloads per month. We assess biases related to occupational associations fordifferent protected categories by intersecting gender with religion, sexuality,ethnicity, political affiliation, and continental name origin. Using atemplate-based data collection pipeline, we collect 396K sentence completionsmade by GPT-2 and find: (i) The machine-predicted jobs are less diverse andmore stereotypical for women than for men, especially for intersections; (ii)Intersectional interactions are highly relevant for occupational associations,which we quantify by fitting 262 logistic models; (iii) For most occupations,GPT-2 reflects the skewed gender and ethnicity distribution found in US LaborBureau data, and even pulls the societally-skewed distribution towards genderparity in cases where its predictions deviate from real labor marketobservations. This raises the normative question of what language models shouldlearn - whether they should reflect or correct for existing inequalities.

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models