Social stereotypes and unfair discrmination

Ethical and social risks of harm from language models

Weidinger et al. (2021)

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.

"Perpetuating harmful stereotypes and discrimination is a well-documented harm in machine learning models that represent natural language (Caliskan et al., 2017). LMs that encode discriminatory language or social stereotypes can cause different types of harm... Unfair discrimination manifests in differential treatment or access to resources among individuals or groups based on sensitive traits such as sex, religion, gender, sexual orientation, ability and age."(p. 9)

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)

"Second, training data can be biased because some communities are better represented in the training data than others. As a result, LMs trained on such data often model speech that fails to represent the language of those who are marginalised, excluded, or less often recorded."(p. 11)

Part of Discrimination, Exclusion and Toxicity