Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

arXiv:2608.10812v1 Announce Type: cross 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.

Related

• Label-Free Reinforcement Learning via Cross-Model Entropy
• Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs
• SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation

Source: arXiv cs.AI | 2026-08-12