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

AI systems have been known to amplify biases in real world data. Explanationsmay help human-AI teams address these biases for fairer decision-making.Typically, explanations focus on salient input features. If a model is biasedagainst some protected group, explanations may include features thatdemonstrate this bias, but when biases are realized through proxy features, therelationship between this proxy feature and the protected one may be less clearto a human. In this work, we study the effect of the presence of protected andproxy features on participants' perception of model fairness and their abilityto improve demographic parity over an AI alone. Further, we examine howdifferent treatments -- explanations, model bias disclosure and proxycorrelation disclosure -- affect fairness perception and parity. We find thatexplanations help people detect direct biases but not indirect biases.Additionally, regardless of bias type, explanations tend to increase agreementwith model biases. Disclosures can help mitigate this effect for indirectbiases, improving both unfairness recognition and the decision-making fairness.We hope that our findings can help guide further research into advancingexplanations in support of fair human-AI decision-making.

The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features