研究提示词设计如何影响手机端大模型的耗能，发现提示复杂度和表达方式显著影响能耗。
How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?
- 通过实测分析提示的认知负荷与表达模式对能耗的影响
- 认知负荷影响每字耗能，表达模式主要通过调用字数改变总耗能
- 不同模型需定制提示策略以实现节能，适合移动设备部署者参考
大型语言模型（LLMs）正越来越多地部署在移动设备上，能源效率成为关键部署约束，但提示设计对能耗的影响仍缺乏研究。本文旨在理解两个提示属性——认知负荷和表达模式——如何影响设备端LLM推理的能耗行为。我们开展了一项广泛的实证研究，涵盖提示属性、数据集、模型与设备，并采用逐阶段剖析技术分离预填充与解码阶段的能耗。研究发现，认知负荷主要影响每令牌的能耗，而表达模式则通过改变令牌使用量显著影响整体能耗。进一步的能效-质量分析表明，提示设计对不同模型的可达成性能边界影响各异，凸显了在设备端高效推理中需考虑模型特性的提示设计。代码、数据集与脚本见 https://amai-gsu.github.io/PromptProperty/。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly deployed on mobile devices, making energy efficiency a key deployment constraint, yet the energy impact of prompt design remains underexplored. This paper aims to understand how two prompt properties, cognitive load and phrasing pattern, shape the energy behavior of on-device LLM inference. We conduct a broad empirical study covering prompt properties, datasets, models, and devices, with phase-level profiling that separates prefill and decode energy. We find that cognitive load primarily affects the energy cost per token, while phrasing pattern affects energy largely through token usage. Our energy-quality analysis further shows that prompt design reshapes the attainable frontier differently across models, highlighting the need for model-aware prompt design in energy-efficient on-device LLM inference. Code, datasets, and scripts are available at https://amai-gsu.github.io/PromptProperty/.
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。