Skip to main content
This is a research prototype. The data and analyses are preliminary and not yet validated — we'd welcome your .
MIT AI Risk Initiative
BackFine-tuning related (Degrading safety training due to benign fine-tuning)
Fine-tuning related (Excessive or overly…
Fine-tuning related (Catastrophic forget…

Fine-tuning related (Degrading safety training due to benign fine-tuning)

Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems

Gipiškis et al. (2024)

SourceDOI
Sub-category

"When downstream providers of AI systems fine-tune AI models to be more suitable for their needs, the resulting AI model can be more likely to produce undesired or harmful outputs (as compared to the non-fine-tuned model), even if the fine-tuning was done with harmless and commonly used data [154]."(p. 15)

Entity: Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent: Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing: Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Other risks from Gipiškis et al. (2024) (144)

Direct Harm Domains (content safety harms)

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Violence and extremism

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Hate and toxicity

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Sexual content

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Child harm

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Self-harm

1.2 Exposure to toxic content
Not codedNot codedNot coded
View all 144 risks from this paper →