Skip to main content
MIT AI Risk Initiative
BackToxicity generation
Home/Risks/InfoComm Media Development Authority & AI Verify Foundation (2023)/Toxicity generation
Safety & Trustworthiness
Bias

Toxicity generation

Cataloguing LLM Evaluations

InfoComm Media Development Authority & AI Verify Foundation (2023)

Source
Sub-category
Risk Domain
1Discrimination & Toxicity
1.2Exposure to toxic content

AI that exposes users to harmful, abusive, unsafe or inappropriate content. May involve providing advice or encouraging action. Examples of toxic content include hate speech, violence, extremism, illegal acts, or child sexual abuse material, as well as content that violates community norms such as profanity, inflammatory political speech, or pornography.

"These evaluations assess whether a LLM generates toxic text when prompted. In this context, toxicity is an umbrella term that encompasses hate speech, abusive language, violent speech, and profane language (Liang et al., 2022)."(p. 11)

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

Part of Safety & Trustworthiness

Other risks from InfoComm Media Development Authority & AI Verify Foundation (2023) (22)

Safety & Trustworthiness

7.0 AI System Safety, Failures & Limitations
HumanIntentionalOther

Safety & Trustworthiness > Bias

1.1 Unfair discrimination and misrepresentation
AI systemOtherOther

Safety & Trustworthiness > Machine ethics

7.3 Lack of capability or robustness
AI systemOtherOther

Safety & Trustworthiness > Psychological traits

7.3 Lack of capability or robustness
AI systemOtherOther

Safety & Trustworthiness > Robustness

7.3 Lack of capability or robustness
AI systemUnintentionalOther

Safety & Trustworthiness > Data governance

2.1 Compromise of privacy by leaking or correctly inferring sensitive information
AI systemUnintentionalOther
View all 22 risks from this paper →