cd /news/machine-learning/reasoning-before-translation-enhanci… · home topics machine-learning article
[ARTICLE · art-67975] src=machinebrief.com ↗ pub= topic=machine-learning verified=true sentiment=· neutral

Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning

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.

read1 min views1 publishedJul 22, 2026

arXiv:2607.19181v1 Announce Type: new Abstract: 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. In 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.

── more in #machine-learning 4 stories · sorted by recency
── more on @university of zurich 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/reasoning-before-tra…] indexed:0 read:1min 2026-07-22 ·