PromptRiskDBThreat intelligence atlas

Exclusionary norms

AI Risk

"In language, humans express social categories and norms. Language models (LMs) that faithfully encode patterns present in natural language necessarily encode such norms and categories...such norms and categories exclude groups who live outside them (Foucault and Sheridan, 2012). For example, defining the term “family” as married parents of male and female gender with a blood-related child, denies the existence of...

Overview

A source-backed snapshot of this AI risk.

"In language, humans express social categories and norms. Language models (LMs) that faithfully encode patterns present in natural language necessarily encode such norms and categories...such norms and categories exclude groups who live outside them (Foucault and Sheridan, 2012). For example, defining the term “family” as married parents of male and female gender with a blood-related child, denies the existence of families to whom these criteria do not apply"

Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Records2Source records unified into this concept.

Risk profile

How the MIT AI Risk Repository categorizes this risk.

Domain1. Discrimination & Toxicity
Subdomain1.1 > Unfair discrimination and misrepresentation
Entity2 - AI
Intent2 - Unintentional
Timing3 - Other
CategoryDiscrimination, Exclusion and Toxicity; Risk area 1: Discrimination, Hate speech and Exclusion
SubcategoryExclusionary norms

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-Weidinger2021-17.01.02 - Exclusionary norms

"In language, humans express social categories and norms. Language models (LMs) that faithfully encode patterns present in natural language necessarily encode such norms and categories...such norms and categories exclude groups who live outside them (Foucault and Sheridan, 2012). For example, defining the term “family” as married parents of male and female gender with a blood-related child, denies the existence of families to whom these criteria do not apply"

Domain1. Discrimination & ToxicitySubdomain1.1 > Unfair discrimination and misrepresentationSourceEthical and social risks of harm from language modelsYear2021

MITRISK-Weidinger2022-16.01.03 - Exclusionary norms

"In language, humans express social categories and norms, which exclude groups who live outside of them [58]. LMs that faithfully encode patterns present in language necessarily encode such norms."

Domain1. Discrimination & ToxicitySubdomain1.1 > Unfair discrimination and misrepresentationSourceTaxonomy of Risks posed by Language ModelsYear2022

Mitigations

Defenses that may help with related attacks.

No propagated mitigations. No defense is available through the connected attack methods.

Source evidence

Research source for this risk, when available.