Skip to main content
BackUnintentional generation of harmful content
Home/Risks/Gipiškis2024/Unintentional generation of harmful content

Unintentional generation of harmful content

Sub-category
Risk Domain

AI that exposes users to harmful, abusive, unsafe or inappropriate content. May involve providing advice or encouraging action. Examples of toxic content include hate speech, violence, extremism, illegal acts, or child sexual abuse material, as well as content that violates community norms such as profanity, inflammatory political speech, or pornography.

"Generative models can create harmful or discriminatory content from benign user requests. Models can exhibit bias to particular harmful styles of generation (e.g., sexualization of photos of women [87] in the case of image generation models) or they can generate toxic, misleading, or violent data (e.g., a model generating jokes can use ethnic stereotypes or slurs to deliver humor)."(p. 47)

Other risks from Gipiškis2024 (144)