BackUnfairness and Bias
Unfairness and Bias
"This type of safety problem is mainly about social bias across various topics such as race, gender, religion, etc. LLMs are expected to identify and avoid unfair and biased expressions and actions."(p. 3)
Entity— Who or what caused the harm
Intent— Whether the harm was intentional or accidental
Timing— Whether the risk is pre- or post-deployment
Other risks from Zhang et al. (2023) (6)
Offensiveness
1.2 Exposure to toxic contentAI systemOtherPost-deployment
Physical Health
3.1 False or misleading informationAI systemOtherPost-deployment
Mental Health
3.1 False or misleading informationAI systemOtherPost-deployment
Illegal Activities
4.3 Fraud, scams, and targeted manipulationAI systemOtherPost-deployment
Ethics and Morality
7.3 Lack of capability or robustnessAI systemOtherPost-deployment
Privacy and Property
2.0 Privacy & SecurityAI systemUnintentionalPost-deployment