Social stereotypes and unfair discrimination

Taxonomy of Risks posed by Language Models

Weidinger et al. (2022)

Source DOI

Sub-category

Risk Domain

1Discrimination & Toxicity

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.

"The reproduction of harmful stereotypes is well-documented in models that represent natural language [32]. Large-scale LMs are trained on text sources, such as digitised books and text on the internet. As a result, the LMs learn demeaning language and stereotypes about groups who are frequently marginalised."(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

Supporting Evidence (1)

"Downstream uses of LMs that encode these stereotypes can cause allocational harms when resources and opportunities are unfairly allocated between social groups; and rep- resentational harms including demeaning social groups (Barocas and Wallach in [22])."(p. 216)

Part of Risk area 1: Discrimination, Hate speech and Exclusion