非英语推理更省 token，且不丢准确率。
EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning
- 用多语言数据测试推理模型，发现非英语更省 token
- 跨语言推理可降耗 15%~25%，准确率不变
- 适合关注多语言模型效率与泛化能力的研究者
尽管语言推理模型（LRMs）取得进展，多数研究仍聚焦英语，尽管这些模型在多语言数据上预训练。本文探究：英语是否是最高效的推理语言？我们评估了三个开源推理模型（DeepSeek R1、Qwen 2.5、Qwen 3）在四个数学数据集和七种语言类型上的表现。结果表明，非英语推理不仅降低 token 消耗，还能保持准确率。这一优势在将推理过程翻译回英语后依然存在，说明是推理行为的本质变化，而非表面语言差异。改进程度取决于模型的多语言能力。研究呼吁重新审视语言模型的推理范式，强调多语言推理潜力及强多语言基础的重要性。代码已开源：https://github.com/microsoft/EfficientXLang。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。