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

All AI models are susceptible to learning biases in data that they aretrained on. For generative dialogue models, being trained on real humanconversations containing unbalanced gender and race/ethnicity references canlead to models that display learned biases, which we define here broadly as anymeasurable differences in the distributions of words or semantic content ofconversations based on demographic groups. We measure the strength of suchbiases by producing artificial conversations between two copies of a dialoguemodel, conditioning one conversational partner to state a name commonlyassociated with a certain gender and/or race/ethnicity. We find that largercapacity models tend to exhibit more gender bias and greater stereotyping ofoccupations by gender. We show that several methods of tuning these dialoguemodels, specifically name scrambling, controlled generation, and unlikelihoodtraining, are effective in reducing bias in conversation, including on adownstream conversational task. Name scrambling is also effective in loweringdifferences in token usage across conversations where partners have namesassociated with different genders or races/ethnicities.

Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models