BackDiscriminatory and exclusionary language

Discriminatory and exclusionary language

Emerging Risks and Mitigations for Public Chatbots: LILAC v1

Stanley & Lettie (2024)

Sub-category

Risk Domain

1.1Unfair discrimination and misrepresentation

Unequal treatment of individuals or groups by AI, often based on race, gender, or other sensitive characteristics, resulting in unfair outcomes and unfair representation of those groups.

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 Serves as object of personal fantasy, violence, and abuse

Other risks from Stanley & Lettie (2024) (28)

False information

3.1 False or misleading information

AI systemOtherOther

Performative utterances

7.3 Lack of capability or robustness

AI systemUnintentionalPost-deployment

Information enabling malicious actions

1.2 Exposure to toxic content

AI systemOtherPost-deployment

Bad advice/failure to generate helpful content

7.3 Lack of capability or robustness

AI systemUnintentionalOther

Leakage

2.1 Compromise of privacy by leaking or correctly inferring sensitive information

AI systemUnintentionalOther

Toxic and disrespectful content

1.2 Exposure to toxic content

AI systemUnintentionalPost-deployment

View all 28 risks from this paper →