优化提示词可显著降低手机端大模型的耗电量
Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting
- 通过实测发现不同动词和指令结构影响解码长度
- 特定动词使能耗差异达27%，提示词设计能省电
- 适合移动端部署、关注能效的LLM研究者
大型语言模型（LLMs）正越来越多地部署在移动和嵌入式设备上，以提升隐私保护并减少网络延迟。然而，设备端推理面临根本性挑战：在电池供电、资源受限的硬件上存在高能耗问题。尽管模型压缩和运行时加速已广泛研究，但提示词设计对能效的影响仍缺乏探索。本文通过在智能手机上进行真实功耗测量，实证研究了提示词措辞与能耗之间的关系。结果表明，语言特征尤其是祈使类关键词和指令结构会影响解码长度与总能耗，不同动词和任务间呈现稳定的能耗差异，说明提示工程是提升设备端能效的轻量级有效手段。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly deployed on mobile and embedded devices to improve privacy and reduce network latency. Yet on-device inference faces a fundamental constraint: high energy consumption on battery-powered, resource-limited hardware. While model compression and runtime acceleration have been widely studied, the effect of \emph{prompt design} on energy efficiency remains underexplored. This paper presents an empirical study of the relationship between prompt wording and energy consumption for on-device LLMs. Using real power measurements collected on a smartphone, we quantify how linguistic features, particularly imperative keywords and instruction structure, affect decoding length and total energy. Our results show consistent energy differences across verbs and tasks, indicating that prompt engineering is a lightweight lever for improving 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。