Skip to content

R0040/2026-03-28/Q001/S02/R03

Research R0040 — RLHF Alternatives
Run 2026-03-28
Query Q001
Search S02
Result S02-R03

Original Anthropic paper on Constitutional AI.

Summary

Field Value
Title Constitutional AI: Harmlessness from AI Feedback
URL https://arxiv.org/abs/2212.08073
Date accessed 2026-03-28
Publication date 2022-12-15
Author(s) Yuntao Bai et al. (Anthropic)
Publication arXiv (Anthropic Research)

Selection Decision

Included in evidence base: Yes

Rationale: Primary source for Constitutional AI. Establishes the methodology that became the foundation of RLAIF and Anthropic's entire alignment approach for Claude.