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

Traditional algorithmic fairness notions rely on label feedback, which canonly be elicited from expert critics. However, in most practical applications,several non-expert stakeholders also play a major role in the system and canhave distinctive opinions about the decision making philosophy. For example, inkidney placement programs, transplant surgeons are very wary about acceptingkidney offers for black patients due to genetic reasons. However, non-expertstakeholders in kidney placement programs (e.g. patients, donors and theirfamily members) may misinterpret such decisions from the perspective of socialdiscrimination. This paper evaluates group fairness notions from the viewpointof non-expert stakeholders, who can only provide binary\emph{agreement/disagreement feedback} regarding the decision in context.Specifically, two types of group fairness notions have been identified: (i)\emph{definite notions} (e.g. calibration), which can be evaluated exactlyusing disagreement feedback, and (ii) \emph{indefinite notions} (e.g. equalopportunity) which suffer from uncertainty due to lack of label feedback. Inthe case of indefinite notions, bounds are presented based on disagreementrates, and an estimate is constructed based on established bounds. The efficacyof all our findings are validated empirically on real human feedback dataset.

Towards Inclusive Fairness Evaluation via Eliciting Disagreement Feedback from Non-Expert Stakeholders