OTPO uses unbalanced optimal transport to reweight token-level log-likelihood ratios in DPO, reporting up to 10.9% higher length-controlled win rate on AlpacaEval2 than DPO.
The waves dance under the moon, a melody soft and bright
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization
OTPO uses unbalanced optimal transport to reweight token-level log-likelihood ratios in DPO, reporting up to 10.9% higher length-controlled win rate on AlpacaEval2 than DPO.