ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning

TL;DR

This paper introduces ExTrans, a multilingual deep reasoning translation model enhanced by exemplar-based reinforcement learning, achieving state-of-the-art results across multiple languages and outperforming existing large reasoning models.

Contribution

It proposes a novel reward modeling method comparing translation outputs with a strong LRM, and extends this approach to multilingual translation with impressive results.

Findings

Achieves state-of-the-art literary translation performance.

Outperforms large reasoning models like OpenAI-o1 and DeepSeek-R1.

Successfully extends to 11 languages with high translation quality.

Abstract

In recent years, the emergence of large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, has shown impressive capabilities in complex problems, e.g., mathematics and coding. Some pioneering studies attempt to bring the success of LRMs in neural machine translation (MT). They try to build LRMs with deep reasoning MT ability via reinforcement learning (RL). Despite some progress that has been made, these attempts generally focus on several high-resource languages, e.g., English and Chinese, leaving the performance on other languages unclear. Besides, the reward modeling methods in previous work do not fully unleash the potential of reinforcement learning in MT. In this work, we first design a new reward modeling method that compares the translation results of the policy MT model with a strong LRM (i.e., DeepSeek-R1-671B), and quantifies the comparisons to provide rewards. Experimental results demonstrate the superiority of the reward modeling method. Using Qwen2.5-7B-Instruct as the backbone, the trained model achieves the new state-of-the-art performance in literary translation, and outperforms strong LRMs including OpenAI-o1 and DeepSeeK-R1. Furthermore, we extend our method to the multilingual settings with 11 languages. With a carefully designed lightweight reward modeling in RL, we can simply transfer the strong MT ability from a single direction into multiple (i.e., 90) translation directions and achieve impressive multilingual MT performance.