Pith. sign in

REVIEW 2 cited by

Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution

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

arxiv 2402.11525 v3 pith:KIVSEI3C submitted 2024-02-18 cs.CL cs.LG

classification cs.CLcs.LG
keywords translationhumanmachinepreferencequalityrlhftextitlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \textit{BLEU} do not strictly align with human preference of translation quality. In this paper, we explore leveraging reinforcement learning with human feedback (\textit{RLHF}) to improve translation quality. It is non-trivial to collect a large high-quality dataset of human comparisons between translations, especially for low-resource languages. To address this issue, we propose a cost-effective preference learning strategy, optimizing reward models by distinguishing between human and machine translations. In this manner, the reward model learns the deficiencies of machine translation compared to human and guides subsequent improvements in machine translation. Experimental results demonstrate that \textit{RLHF} can effectively enhance translation quality and this improvement benefits other translation directions not trained with \textit{RLHF}. Further analysis indicates that the model's language capabilities play a crucial role in preference learning. A reward model with strong language capabilities can more sensitively learn the subtle differences in translation quality and align better with real human translation preferences.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice

    cs.CL 2025-07 conditional novelty 6.0 of 10

    An end-to-end simultaneous speech-to-speech translation model with voice cloning, trained with a two-stage reinforcement learning reward scheme, reports high accuracy and low latency on the authors' RealSI benchmark.

  2. CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation

    cs.CL 2025-01 conditional novelty 6.0 of 10

    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.

Pith tools