{"slug": "reasoning-before-translation-enhancing-legal-machine-translation-with-structured", "title": "Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning", "summary": "A new study from researchers at the University of Zurich finds that reinforcement learning with verifiable rewards surpasses supervised fine-tuning for legal neural machine translation, though enhanced small models still trail frontier reasoning models. Testing on Swiss multilingual statutes, the team evaluated Qwen3.5 4B, Qwen3.5 9B, and Gemma 3 12B, showing that re-training paradigms yield diminishing returns as model size increases. The code and models are publicly available on GitHub.", "body_md": "arXiv:2607.19181v1 Announce Type: new\nAbstract: Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of precision it requires. The recent emergence of reasoning-capable language models opens new possibilities for tackling such challenges. They add to a set of other previously proposed techniques to enhance the translation quality, which includes supervised fine-tuning and reinforcement learning.\nIn this work, we perform a comparison between these various approaches. More particularly, we evaluate small language models such as Qwen3.5 4B, Qwen3.5 9B, and Gemma 3 12B enhanced with various re-training paradigms and compare their performances against frontier reasoning models. We focus on the Swiss legal system, which -- with its unique multilingual statutes -- offers a particularly challenging testbed for reasoning-augmented models. Our results show that the quality of small ``base'' models can be greatly enhanced, and that reinforcement learning with verifiable rewards can be applied to NMT in the legal domain and surpasses the translation quality of supervised fine-tuning. The performance of enhanced small models is close to the one of state-of-the-art reasoning models yet remains inferior. We also note that re-training paradigms yield diminishing returns as model size increase. The code and models are publicly available at https://github.com/aixiuxiuxiu/Legal-MT-SFT-RL.", "url": "https://wpnews.pro/news/reasoning-before-translation-enhancing-legal-machine-translation-with-structured", "canonical_source": "https://www.machinebrief.com/news/reasoning-before-translation-enhancing-legal-machine-transla-2vbv", "published_at": "2026-07-22 04:00:00+00:00", "updated_at": "2026-07-22 04:10:01.306640+00:00", "lang": "en", "topics": ["machine-learning", "natural-language-processing", "ai-research", "large-language-models"], "entities": ["University of Zurich", "Qwen3.5 4B", "Qwen3.5 9B", "Gemma 3 12B", "arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/reasoning-before-translation-enhancing-legal-machine-translation-with-structured", "markdown": "https://wpnews.pro/news/reasoning-before-translation-enhancing-legal-machine-translation-with-structured.md", "text": "https://wpnews.pro/news/reasoning-before-translation-enhancing-legal-machine-translation-with-structured.txt", "jsonld": "https://wpnews.pro/news/reasoning-before-translation-enhancing-legal-machine-translation-with-structured.jsonld"}}