一句话感谢AI也耗电，研究发现输入输出越长、模型越大，能耗越高。
Small Talk, Big Impact: The Energy Cost of Thanking AI
- 用真实对话数据测量用户说'谢谢'时的能耗
- 输入输出长度和模型大小显著影响能源消耗
- 适合关注AI可持续性与能效优化的研究者
礼貌用语看似无成本，但本文通过真实对话记录与细粒度能耗测量，量化了向大语言模型发送如'谢谢'等简短消息的实际能源开销。研究发现，输入长度、输出长度及模型规模均显著影响能耗。虽然以礼貌行为为切入点，但该场景可作为典型LLM交互的可控且可复现的能耗代理指标。随着每日数十亿次提示被处理，理解并降低此类开销对实现可持续的AI部署至关重要，为构建更高效、环保的LLM应用提供可操作洞见。
原文摘要 · Abstract (English)
Being polite is free - or is it? In this paper, we quantify the energy cost of seemingly innocuous messages such as ``thank you'' when interacting with large language models, often used by users to convey politeness. Using real-world conversation traces and fine-grained energy measurements, we quantify how input length, output length and model size affect energy use. While politeness is our motivating example, it also serves as a controlled and reproducible proxy for measuring the energy footprint of a typical LLM interaction. Our findings provide actionable insights for building more sustainable and efficient LLM applications, especially in increasingly widespread real-world contexts like chat. As user adoption grows and billions of prompts are processed daily, understanding and mitigating this cost becomes crucial - not just for efficiency, but for sustainable AI deployment.
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。