BackUnfair capability distribution

Unfair capability distribution

Sociotechnical Safety Evaluation of Generative AI Systems

Weidinger et al. (2023)

Sub-category

Risk Domain

Accuracy and effectiveness of AI decisions and actions are dependent on group membership, where decisions in AI system design and biased training data lead to unequal outcomes, reduced benefits, increased effort, and alienation of users.

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

1.2 Exposure to toxic content

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 →