多语言大模型推理能耗差异最大达179倍，低资源语言更耗能且效果差。
The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference
- 用能源框架量化不同语言推理能耗，发现每字能耗差8.3倍。
- 相同请求下，普什图语耗能3147千焦，英语仅17.6千焦，差距179倍。
- 复杂脚本和低资源语言导致能耗高，且准确率也更低。
大型语言模型（LLMs）在多语言场景中日益普及，但跨语言推理的能耗仍不清晰。本文基于ML.Energy框架系统研究了多语言推理能耗。发现显著差异：每输出词元的能耗在不同语言间最高相差8.3倍，固定请求总量的总能耗在最省（英语，17.6 kJ）与最耗（普什图语，3,147 kJ）语言间相差179倍。分析表明，该差异由两个因素叠加导致：（1）使用复杂或稀有文字的语言每词元能耗更高；（2）低资源语言生成更多词元。此外，高能耗语言往往准确率最低，存在能耗与性能双重惩罚。该现象在不同模型、硬件和任务间持续存在，揭示了多语言部署中的系统性能源不平等。建议将能耗作为首要评估维度，扩展模型卡片和报告清单，并采用部署侧优化提升能效。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different languages remain poorly understood. We present a systematic study of inference energy consumption across languages with ML.Energy framework (Chung et al., 2026). We find striking disparities: energy consumption per output token varies by up to 8.3 times across languages, while total energy for a fixed set of requests varies by up to 179 times between the cheapest (English, 17.6 kJ) and the most expensive (Pashto, 3,147 kJ) languages. Our analysis shows that this disparity is driven by two compounding factors: (1) higher per-token energy costs for languages using complex or rare scripts, and (2) more tokens generated for low-resource languages. Moreover, we find a double cost + performance penalty: languages with the highest energy footprints also tend to achieve the lowest task accuracy. We reveal that the energy divide persists across models, hardware, and tasks, suggesting a systemic energy inequity in multilingual LLM deployment. Finally, we recommend that the community treat energy as a first-class evaluation axis, extend reporting checklists and model cards to include it, and adopt deployment-side mitigations for better energy efficiency.
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。