SVGT adds independent value modules and Bridge Tokens to LLMs to maintain consistent value guidance, cutting harmful outputs by over 70% in tests while preserving fluency.
Shai and Lucas Teixeira and Alexander Gietelink Oldenziel and Sarah Marzen and Paul M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
SVGT adds independent value modules and Bridge Tokens to LLMs to maintain consistent value guidance, cutting harmful outputs by over 70% in tests while preserving fluency.