A reliable-to-expressive curriculum with dynamic rubrics trains a 12B safety judge to achieve 94%+ accuracy with only 0.76 cross-rubric variance on three different rubric prompts.
Gemma Team, G
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
A reliable-to-expressive curriculum with dynamic rubrics trains a 12B safety judge to achieve 94%+ accuracy with only 0.76 cross-rubric variance on three different rubric prompts.