Preference-tuning a weak model on whether its drafts improve a strong model's outputs makes the weak-strong pair outperform both models alone.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Synergistic Weak-Strong Collaboration by Aligning Preferences
Preference-tuning a weak model on whether its drafts improve a strong model's outputs makes the weak-strong pair outperform both models alone.