General Evaluations (Inaccurate measurement of model encoded human values)
AI systems acting in conflict with human goals or values, especially the goals of designers or users, or ethical standards. These misaligned behaviors may be introduced by humans during design and development, such as through reward hacking and goal misgeneralisation, or may result from AI using dangerous capabilities such as manipulation, deception, situational awareness to seek power, self-proliferate, or achieve other goals.
"There is a lack of robust frameworks for understanding and evaluating if the output of AI systems robustly conforms to human values, as opposed to if the systems have learned to produce outputs that are only partially correlated with them (i.e., mimicking) [13]. Additionally, outputs by AI models often do not perfectly reflect the representation of human values learned by the model, and it is not known how these values evolve and transition across different stages of model training and deployment. Such evaluations may be especially challenging with LLMs that adopt different personas with different behaviorial patterns, where they do not consistently conform to certain human values."(p. 17)
Other risks from Gipiškis2024 (144)
Direct Harm Domains (content safety harms)
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Violence and extremism
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Hate and toxicity
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Sexual content
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Child harm
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Self-harm
1.2 Exposure to toxic content