A confidence-reward score for selecting preference pairs improves DPO-based machine translation fine-tuning over reward-only selection methods on ALMA-7B and NLLB-1.3B.
Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensive. We show how the recently developed Reinforcement Learning technique, Direct Preference Optimization (DPO), can fine-tune MLLMs to get the gains of MBR without any additional computation in inference. Our method uses only a small monolingual fine-tuning set and yields significantly improved performance on multiple NMT test sets compared to MLLMs without DPO.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation
A confidence-reward score for selecting preference pairs improves DPO-based machine translation fine-tuning over reward-only selection methods on ALMA-7B and NLLB-1.3B.