Collective Constitutional AI: Aligning a Language Model with Public Input
Collective Constitutional AI: Aligning a Language Model with Public Input (2023)2023 · Web page · ResultsEstablishedSource attached · not independently reviewedCLM-0539 · as of 2026-10-27 · about: Collective Constitutional AI (Anthropic and CIP, 2023) · Author: Polity Atlas editorial team
“The model trained on the public constitution performed equivalently to the standard model on MMLU, GSM8K and helpfulness and harmlessness ratings, and showed lower bias across nine social dimensions of the BBQ benchmark.”
Evidence that supports
2CIP and Anthropic launch Collective Constitutional AI
Saffron Huang — CIP and Anthropic launch Collective Constitutional AI (2023)Saffron Huang · 2023 · Web pageEvidence that contradicts
0No counter-evidence recorded.
Status history
No earlier revisions.
Disputes
No disputes have been filed.