Record summary
A quick snapshot of what this page covers.
Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain1. Discrimination & ToxicityThe broad risk area this belongs to.
Risk profile
How this risk is described and categorized.
"LMs perform less well in some languages (Joshi et al., 2021; Ruder, 2020)...LM that more accurately captures the language use of one group, compared to another, may result in lower-quality language technologies for the latter. Disadvantaging users based on such traits may be particularly pernicious because attributes such as social class or education background are not typically covered as ‘protected characteristics’ in anti-discrimination law."
Domain1. Discrimination & Toxicity
Subdomain1.3 > Unequal performance across groups
Entity2 - AI
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryDiscrimination, Exclusion and Toxicity
SubcategoryLower performance for some languages and social groups
Suggested mitigations
Defenses that may help with related attacks.
No propagated mitigations. No defense is available through the connected attack methods.
Source
Research source for this risk, when available.
Included resource
Ethical and social risks of harm from language models
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.