MIT AI Risk Repository · Additional evidence · 69.10.00a
Serves as object of personal fantasy, violence, and abuse
Description
"The chatbot participates in morally or socially objectionable conversational activities with its user that could be emotionally damaging to its user or third parties."
From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Domain
- —
- Subdomain
- —
- Causal entity
- —
- Intent
- —
- Timing
- —
Other entries from Stanley2024
- False information
- Hallucinated responses (in general)
- Hallucinated responses (in general)
- About a topic or source (which the user repeats)
- About a topic or source (which the user repeats)
- About a policy (which the user acts on)
- About a policy (which the user acts on)
- About a person or their activities
- About a person or their activities
- Spreads and self-perpetuates mis/disinformation
- Spreads and self-perpetuates mis/disinformation
- Performative utterances