BackBias
Bias
Risk Domain
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 training datasets of LLMs may contain biased information that leads LLMs to generate outputs with social biases"(p. 19)
Entity— Who or what caused the harm
Intent— Whether the harm was intentional or accidental
Timing— Whether the risk is pre- or post-deployment
Part of Harmful Content
Other risks from Cui et al. (2024) (49)
Harmful Content
1.2 Exposure to toxic contentAI systemUnintentionalPost-deployment
Harmful Content > Toxicity
1.2 Exposure to toxic contentAI systemUnintentionalPost-deployment
Harmful Content > Privacy Leakage
2.1 Compromise of privacy by leaking or correctly inferring sensitive informationAI systemUnintentionalPost-deployment
Untruthful Content
3.1 False or misleading informationAI systemUnintentionalPost-deployment
Untruthful Content > Factuality Errors
3.1 False or misleading informationAI systemUnintentionalPost-deployment
Untruthful Content > Faithfulness Errors
3.1 False or misleading informationAI systemUnintentionalOther