| title | Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation |
|---|---|
| authors | Chris Han, Pengzhi Gao, Pei Fu, Jian Luan |
| date | 2026-08-11 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2608.10812 |
| affiliation | Xiaomi Research |
| upvotes | 8 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiLMMT-46-v0.1 models, we apply Group Relative Policy Optimization (GRPO) with a reward that averages two reference-free quality estimation models and is gated by language identification. We then linearly interpolate the supervised fine-tuning (SFT) and reinforcement learning (RL) model checkpoints to obtain MiLMMT-46-v1.0. Across 46 languages, the resulting models consistently improve translation quality over their SFT counterparts, outperform strong recent open baselines, including Seed-X, HY-MT2, and TranslateGemma, and achieve leading reference-free scores against evaluated proprietary systems such as Google Translate, Gemini 3 Pro, and GPT-5. We further investigate on-policy distillation and find that it reaches, but does not surpass, the quality frontier achieved by RL with checkpoint interpolation. We release the models and code to facilitate future research. |
cite
@misc{han2026reference,
title={Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation},
author={Chris Han and Pengzhi Gao and Pei Fu and Jian Luan},
year={2026},
eprint={2608.10812},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.10812}
}