REVIEW 1 cited by
Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 1 Pith paper
-
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.
Discussion (0). Continue with ORCID to comment.