{
  "id": 18376,
  "url": "https://arxiv.org/abs/2608.10812",
  "title": "Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation",
  "summary": "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 re",
  "authors": "Chris Han, Pengzhi Gao, Pei Fu, Jian Luan",
  "category": "research",
  "topics": "regulation",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T20:00:00.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/18376",
  "original_url": "https://arxiv.org/abs/2608.10812",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}