Statements (24)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:AI_alignment_technique
|
| gptkbp:aimsTo |
align AI behavior with human values
|
| gptkbp:alternativeTo |
gptkb:RLHF
|
| gptkbp:appliesTo |
language models
|
| gptkbp:citation |
https://arxiv.org/abs/2212.08073
|
| gptkbp:describedInPaper |
gptkb:Constitutional_AI:_Harmlessness_from_AI_Feedback
|
| gptkbp:developedBy |
gptkb:Anthropic
|
| gptkbp:firstDescribed |
2022
|
| gptkbp:focusesOn |
helpfulness
honesty harmlessness |
| gptkbp:goal |
reduce reliance on human feedback
|
| gptkbp:influencedBy |
constitutional law concepts
|
| gptkbp:involves |
revisions based on principles
self-critiquing |
| gptkbp:relatedTo |
AI safety
AI alignment |
| gptkbp:usedBy |
gptkb:Claude_AI_models
|
| gptkbp:uses |
AI-generated feedback
set of principles or constitution |
| gptkbp:bfsParent |
gptkb:Anthropic
gptkb:Claude |
| gptkbp:bfsLayer |
6
|
| https://www.w3.org/2000/01/rdf-schema#label |
Constitutional AI
|