Article
Constitutional AI: Harmlessness from AI Feedback
Yuntao Bai; et al. · arXiv preprint 2212.08073 (Anthropic) · 2022
- Type
- Article
- Author
- Yuntao Bai; et al.
- Identifier
- DOI 10.48550/arXiv.2212.08073
- Accessed
- 2026-09-01
- Reliability notes
- No journal or conference version listed on arXiv as of October 2026.
Claims citing this source
0 claimsNo published claim cites this source yet.