A method that alternately fine-tunes a policy model with DPO and retrains its reward model on pseudo-preferences drawn from the policy's pre- and post-update outputs, reporting gains on AlpacaEval-2 and RewardBench.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mutual-Taught for Co-adapting Policy and Reward Models
A method that alternately fine-tunes a policy model with DPO and retrains its reward model on pseudo-preferences drawn from the policy's pre- and post-update outputs, reporting gains on AlpacaEval-2 and RewardBench.