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/

Zendy Plus

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

Zendy Tools

Zendy Open

Fairness is a growing concern for high-risk decision-making using ArtificialIntelligence (AI) but ensuring it through purely technical means ischallenging: there is no universally accepted fairness measure, fairness iscontext-dependent, and there might be conflicting perspectives on what isconsidered fair. Thus, involving stakeholders, often without a background in AIor fairness, is a promising avenue. Research to directly involve stakeholdersis in its infancy, and many questions remain on how to support stakeholders tofeedback on fairness, and how this feedback can be integrated into AI models.Our work follows an approach where stakeholders can give feedback on specificdecision instances and their outcomes with respect to their fairness, and thento retrain an AI model. In order to investigate this approach, we conducted twostudies of a complex AI model for credit rating used in loan applications. Instudy 1, we collected feedback from 58 lay users on loan application decisions,and conducted offline experiments to investigate the effects on accuracy andfairness metrics. In study 2, we deepened this investigation by showing 66participants the results of their feedback with respect to fairness, and thenconducted further offline analyses. Our work contributes two datasets andassociated code frameworks to bootstrap further research, highlights theopportunities and challenges of employing lay user feedback for improving AIfairness, and discusses practical implications for developing AI applicationsthat more closely reflect stakeholder views about fairness.

Human-in-the-loop Fairness: Integrating Stakeholder Feedback to Incorporate Fairness Perspectives in Responsible AI