Promoting harmful stereotypes by implying gender or ethnic identity

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.

"A conversational agent may invoke associations that perpetuate harmful stereotypes, either by using particular identity markers in language (e.g. referring to “self” as “female”), or by more general design features (e.g. by giving the product a gendered name)."(p. 31)

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)

Example: "Gender For example, commercially available voice assistants are overwhelmingly represented as submissive and female (Cercas Curry et al., 2020; West et al., 2019). A study of five voice assistants in South Korea found that all assistants were voiced as female, self-described as ‘beautiful’, suggested ‘intimacy and subordination’, and ‘embrace sexual objectification’ (Hwang et al., 2019)."(p. 31)

Part of Human-Computer Interaction Harms