Applying Wasserstein-distance domain adaptation, a known technique, to reward models lets preference signals learned on labeled source data transfer to unlabeled target domains, with consistent but modest gains across four settings.
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
-
Aligning LLMs with Domain Invariant Reward Models
Applying Wasserstein-distance domain adaptation, a known technique, to reward models lets preference signals learned on labeled source data transfer to unlabeled target domains, with consistent but modest gains across four settings.