An external 'superego' module that filters agentic AI plans against user-selected 'constitutions' plus a universal safety floor is reported to cut harmful outputs by up to 98% on safety benchmarks.
Towards an End -to-End Personal Fine -Tuning Framework for AI Value Alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values
An external 'superego' module that filters agentic AI plans against user-selected 'constitutions' plus a universal safety floor is reported to cut harmful outputs by up to 98% on safety benchmarks.