Record summary
A quick snapshot of what this page covers.
Records6Records included in this view.
SourcePublicBuilt from public source data.
ModeStaticPrepared as a ready-to-read page.
Domain summary
A group of related risks from the AI Risk database.
6 AI risk records are grouped under 1.0 > Discrimination & Toxicity in 1. Discrimination & Toxicity.
Domain1. Discrimination & Toxicity
Subdomain1.0 > Discrimination & Toxicity
Risks6
Top categoryRepresentation and Toxicity
Top timing2 - Post-deployment
Risk records
Individual risks in this group.
A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents
2 - Unintentional2 - Post-deployment
A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms
3 - Other3 - Other
Ethical and social risks of harm from language models
2 - Unintentional2 - Post-deployment
Governance of artificial intelligence: A risk and guideline-based integrative framework
2 - Unintentional3 - Other
SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions
3 - Other2 - Post-deployment
Sociotechnical Safety Evaluation of Generative AI Systems
2 - Unintentional2 - Post-deployment
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.