ACTG-ARL uses a hierarchical DP feature-learning plus conditional-generation pipeline followed by anchored RL to raise MAUVE scores by 20% and improve instruction following under privacy constraints.
Strive to include a mix of: – **General-Purpose Features**: Attributes applicable to almost any text (e.g., Formality, Sentiment)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
ACTG-ARL uses a hierarchical DP feature-learning plus conditional-generation pipeline followed by anchored RL to raise MAUVE scores by 20% and improve instruction following under privacy constraints.