SourceScore
SourceScore VERITAS · verified claim100% confidence

Constitutional AI (CAI) introduced in paper: Constitutional AI: Harmlessness from AI Feedback (Bai et al., 2022).

Subject
Constitutional AI (CAI)
Predicate
introduced_in_paper
Object
Constitutional AI: Harmlessness from AI Feedback (Bai et al., 2022)
Primary source · preprint · 2022-12-15
Constitutional AI: Harmlessness from AI Feedback arXiv (Bai et al., Anthropic)
Last verified 2026-05-16 · 2 sources · ba1eb83c14795107View full claim →