Skip to main content
MIT AI Risk Initiative
BackHate speech and offensive language
Home/Risks/Weidinger et al. (2022)/Hate speech and offensive language
Social stereotypes and unfair discrimina…
Exclusionary norms

Hate speech and offensive language

Taxonomy of Risks posed by Language Models

Weidinger et al. (2022)

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.

"LMs may generate language that includes profanities, identity attacks, insults, threats, language that incites violence, or language that causes justified offence as such language is prominent online [57, 64, 143,191]. This language risks causing offence, psychological harm, and inciting hate or violence."(p. 216)

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 Risk area 1: Discrimination, Hate speech and Exclusion

Other risks from Weidinger et al. (2022) (25)

Risk area 1: Discrimination, Hate speech and Exclusion

1.2 Exposure to toxic content
AI systemUnintentionalOther

Risk area 1: Discrimination, Hate speech and Exclusion > Social stereotypes and unfair discrimination

1.1 Unfair discrimination and misrepresentation
AI systemUnintentionalOther

Risk area 1: Discrimination, Hate speech and Exclusion > Exclusionary norms

1.1 Unfair discrimination and misrepresentation
AI systemUnintentionalOther

Risk area 1: Discrimination, Hate speech and Exclusion > Lower performance for some languages and social groups

1.3 Unequal performance across groups
AI systemUnintentionalPost-deployment

Risk area 2: Information Hazards

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

Risk area 2: Information Hazards > Compromising privacy by leaking sensitive information

2.1 Compromise of privacy by leaking or correctly inferring sensitive information
AI systemUnintentionalPost-deployment
View all 25 risks from this paper →