How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation

TL;DR

This paper evaluates the effectiveness of Large Reasoning Models (LRMs) versus traditional Large Language Models (LLMs) in multi-domain machine translation, highlighting LRMs' superior performance in complex, domain-sensitive translation tasks.

Contribution

It provides a comprehensive comparison of LRMs and LLMs across multiple domains and translation directions, demonstrating the advantages of structured reasoning in translation quality.

Findings

LRMs outperform LLMs in semantically complex domains

Structured reasoning improves translation in long-text and high-difficulty scenarios

Domain-adaptive prompting enhances LRM performance

Abstract

Large language models (LLMs) have demonstrated strong performance in general-purpose machine translation, but their effectiveness in complex, domain-sensitive translation tasks remains underexplored. Recent advancements in Large Reasoning Models (LRMs), raise the question of whether structured reasoning can enhance translation quality across diverse domains. In this work, we compare the performance of LRMs with traditional LLMs across 15 representative domains and four translation directions. Our evaluation considers various factors, including task difficulty, input length, and terminology density. We use a combination of automatic metrics and an enhanced MQM-based evaluation hierarchy to assess translation quality. Our findings show that LRMs consistently outperform traditional LLMs in semantically complex domains, especially in long-text and high-difficulty translation scenarios. Moreover, domain-adaptive prompting strategies further improve performance by better leveraging the reasoning capabilities of LRMs. These results highlight the potential of structured reasoning in MDMT tasks and provide valuable insights for optimizing translation systems in domain-sensitive contexts.