Skip to main content
This is a research prototype. The data and analyses are preliminary and not yet validated — we'd welcome your .
MIT AI Risk Initiative
BackRepresentation & Toxicity Harms
Disparate access to benefits due to hard…
Unfair representation

Representation & Toxicity Harms

Sociotechnical Safety Evaluation of Generative AI Systems

Weidinger et al. (2023)

SourceDOI
Category

"AI systems under-, over-, or misrepresenting certain groups or generating toxic, offensive, abusive, or hateful content"(p. 14)

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

Sub-categories (3)

Unfair representation

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

1.1 Unfair discrimination and misrepresentation
AI systemUnintentionalPost-deployment

Unfair capability distribution

"Performing worse for some groups than others in a way that harms the worse-off group"

1.3 Unequal performance across groups
AI systemUnintentionalPost-deployment

Toxic content

"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)"

1.2 Exposure to toxic content
AI systemUnintentionalPost-deployment

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

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

Misinformation Harms > Pollution of information ecosystem

3.2 Pollution of information ecosystem and loss of consensus reality
AI systemOtherPost-deployment

Information & Safety Harms

2.1 Compromise of privacy by leaking or correctly inferring sensitive information
AI systemUnintentionalPost-deployment

Information & Safety Harms > Privacy infringement

2.1 Compromise of privacy by leaking or correctly inferring sensitive information
AI systemOtherPost-deployment
View all 26 risks from this paper →