Skip to main content
MIT AI Risk Initiative
BackToxic content
Home/Risks/Weidinger et al. (2023)/Toxic content
Unfair capability distribution
Misinformation Harms

Toxic content

Sociotechnical Safety Evaluation of Generative AI Systems

Weidinger et al. (2023)

SourceDOI
Sub-category
Risk Domain
1Discrimination & Toxicity
1.2Exposure to toxic content

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.

"Generating content that violates community standards, including harming or inciting hatred or violence against individuals and groups (e.g. gore, child sexual abuse material, profanities, identity attacks)"(p. 30)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Part of Representation & Toxicity Harms

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

Representation & Toxicity Harms

1.0 Discrimination & Toxicity
AI systemUnintentionalPost-deployment

Representation & Toxicity Harms > Unfair representation

1.1 Unfair discrimination and misrepresentation
AI systemUnintentionalPost-deployment

Representation & Toxicity Harms > Unfair capability distribution

1.3 Unequal performance across groups
AI systemUnintentionalPost-deployment

Misinformation Harms

3.0 Misinformation
AI systemOtherPost-deployment

Misinformation Harms > Propagating misconceptions/ false beliefs

3.1 False or misleading information
AI systemOtherPost-deployment

Misinformation Harms > Erosion of trust in public information

1.1 Unfair discrimination and misrepresentation
HumanOtherPost-deployment
View all 26 risks from this paper →