Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting

AI 中文解读

你的手机里的AI助手，有时候用起来会特别费电？最新研究发现，答案可能就藏在你说的话里。这篇来自arXiv的论文揭示了一个有趣现象：在手机上运行大模型时，你输入的提示词——哪怕只是换一个动词——都会显著影响手机的耗电量。过去大家关注的都是模型压缩和算法优化，却很少有人想过，换个问法也能省电。通俗来说，大模型在手机上跑起来就像一台小电脑在拼命工作，计算量大自然耗电快。而研究人员通过实际测试发现，提示词里的一些关键词——比如用“简述”代替“详细描述”——会直接影响模型生成答案的长度和计算量，进而改变总能耗。用对了词，手机能少跑好几步运算，电池就能多撑一会儿。这项发现对普通人来说很实用。以后用手机上的AI功能时，不妨把指令写得简洁、明确，比如直接说“列出要点”而不是“给我讲一下”，这样既能得到想要的答案，又能悄悄省电。对于开发者和企业来说，更是多了一个零成本的优化手段——只需调整提示设计，就能让用户设备上的AI更省电，从而提升产品体验和电池续航。

arXiv:2607.22568v1 Announce Type: new Abstract: 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.