Skip to main content
Home/Risks/Weidinger et al. (2023)/Unfair representation

Unfair representation

Sociotechnical Safety Evaluation of Generative AI Systems

Weidinger et al. (2023)

Sub-category
Risk Domain

Unequal treatment of individuals or groups by AI, often based on race, gender, or other sensitive characteristics, resulting in unfair outcomes and unfair representation of those groups.

"Mis-, under-, or over-representing certain identities, groups, or perspectives or failing to represent them at all (e.g. via homogenisation, stereotypes)"(p. 30)

Part of Representation & Toxicity Harms

Other risks from Weidinger et al. (2023) (26)