# Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning

arXiv: https://arxiv.org/abs/2607.19181 · HTML: https://mlsanity.com/paper/2607.19181/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA](https://mlsanity.com/paper/2312.03732/) (2023)
- [REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization](https://mlsanity.com/paper/2501.03262/) (2025)
- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)
- [GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4](https://mlsanity.com/paper/2310.13988/) (2023)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning](https://mlsanity.com/paper/2504.10160/) (2025)
- [Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning](https://mlsanity.com/paper/2502.19655/) (2025)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis](https://mlsanity.com/paper/2502.11544/) (2025)
- [R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning](https://mlsanity.com/paper/2502.19735/) (2025)
- [New Trends for Modern Machine Translation with Large Reasoning Models](https://mlsanity.com/paper/2503.10351/) (2025)
- [LLMs as Models for Analogical Reasoning](https://mlsanity.com/paper/2406.13803/) (2024)
- [SwiLTra-Bench: The Swiss Legal Translation Benchmark](https://mlsanity.com/paper/2503.01372/) (2025)
- [DeepTrans: Deep Reasoning Translation via Reinforcement Learning](https://mlsanity.com/paper/2504.10187/) (2025)
- [TranslateGemma Technical Report](https://mlsanity.com/paper/2601.09012/) (2026)

## Abstract (arXiv)

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.