General Evaluations (Incorrect outputs of GPAI evaluating other AI models)
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.
"When an LLM is configured to evaluate the performance of another model or AI system, it may produce incorrect evaluation outputs [122, 147]. For example, it may give a higher rating to a more verbose answer or an answer from a particular political stance. If an LLM-based evaluation is integrated into the training of a new model, the trained model could develop in a way that specifically finds and exploits limitations in the evaluator’s metrics."(p. 16)
Other risks from Gipiškis et al. (2024) (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