EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning
This work addresses token efficiency in reasoning for multilingual language models, offering incremental insights into cross-lingual optimization.
The paper investigates whether English is the most token-efficient language for reasoning in language models, finding that reasoning in non-English languages reduces token usage while preserving accuracy across three models and multiple languages.
Despite recent advances in Language Reasoning Models (LRMs), most research focuses solely on English, even though many models are pretrained on multilingual data. In this work, we investigate: Is English the most token-efficient language for reasoning? We evaluate three open-source RLMs: DeepSeek R1, Qwen 2.5 and Qwen 3, across four math datasets and seven typologically diverse languages. We find that reasoning in non-English languages not only reduces token usage, but also preserves accuracy. These gains persist even after translating the reasoning traces into English, suggesting genuine shifts in reasoning behavior rather than surface-level linguistic effects. The extent of improvement, however, depends on the models multilingual strength. Our findings motivate a broader view of reasoning in language models, highlighting the potential of multilingual reasoning and the importance of strong multilingual foundations. The code for our work can be found: https://github.com/microsoft/EfficientXLang.