BackLack of transparency and interpretability
Lack of transparency and interpretability
Risk Domain
Challenges in understanding or explaining the decision-making processes of AI systems, which can lead to mistrust, difficulty in enforcing compliance standards or holding relevant actors accountable for harms, and the inability to identify and correct errors.
"Today's Frontier AI is difficult to interpret and lacks transparency. Contextual understanding of the training data is not explicitly embedded within these models. They can fail to capture perspectives of underrepresented groups or the limitations within which they are expected to perform without fine tuning or reinforcement learning with human feedback (RLHF)."(p. 23)
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 Government Office for Science (2023) (19)
Discrimination
1.1 Unfair discrimination and misrepresentationAI systemUnintentionalPost-deployment
Inequality
6.2 Increased inequality and decline in employment qualityAI systemUnintentionalPost-deployment
Environmental impacts
6.6 Environmental harmHumanUnintentionalPost-deployment
Amplification of biases
1.1 Unfair discrimination and misrepresentationHumanUnintentionalPre-deployment
Harmful responses
1.2 Exposure to toxic contentHumanUnintentionalPre-deployment
Intellectual property rights
6.3 Economic and cultural devaluation of human effortHumanOtherPre-deployment