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

• URL: http://arxiv.org/abs/2607.22568v1
• Date: Sun, 31 May 2026 18:29:16 GMT
• Title: Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting
• Abstract summary: Large Language Models (LLMs) are increasingly deployed on mobile and embedded devices to improve privacy and reduce network latency.<n>Yet on-device inference faces a fundamental constraint: high energy consumption on battery-powered, resource-limited hardware.<n>This paper presents an empirical study of the relationship between prompt wording and energy consumption for on-device LLMs.
• Score: 2.1921490318031656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• How Do Prompt Variations Affect Energy Consumption in On-Device LLMs? [15.386321055792209]
  Large language models (LLMs) are increasingly deployed on mobile devices, making energy efficiency a key deployment constraint.<n>This paper aims to understand how two prompt properties, cognitive load and phrasing pattern, shape the energy behavior of on-device LLM inference.
  arXiv  Detail & Related papers  (2026-09-01T19:08:04Z)
• Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures [0.2519906683279152]
  We study how attention architecture influences decode-phase energy consumption under varying inference workloads.<n>We show that attention is the primary factor governing how decode energy scales with context length.<n>Model size determines absolute energy consumption, while reducing both energy per generated token and latency by up to 87%.
  arXiv  Detail & Related papers  (2026-08-25T19:45:30Z)
• Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use [4.513690948889834]
  Large Language Models (LLMs) are increasingly deployed in production, contributing towards shifting the burden in terms of computational resources and energy demands from training to inference.<n>We show how emphsystem-level design choices can lead to orders-of-magnitude differences in energy consumption for the same model.<n>Our findings motivate phase-aware energy profiling and system-level optimizations for greener AI services.
  arXiv  Detail & Related papers  (2026-01-29T22:16:25Z)
• Green Prompting [2.377736044164336]
  Large Language Models (LLMs) have become widely used across various domains spanning search engines, code generation, and text creation.<n>This study empirically study how different prompt and response characteristics directly impact LLM inference energy cost.
  arXiv  Detail & Related papers  (2025-03-09T19:49:31Z)
• Transformers for Green Semantic Communication: Less Energy, More Semantics [0.3226483876828104]
  "Energy-d Semantic Loss" function addresses the challenge of balancing semantic information loss and energy consumption. It can save up to 90% of energy while achieving a 44% improvement in semantic similarity performance during inference. This work paves the way for energy-efficient neural network selection and the development of greener semantic communication architectures.
  arXiv  Detail & Related papers  (2023-10-11T15:35:20Z)
• In-context Autoencoder for Context Compression in a Large Language Model [70.7621953091318]
  We propose the In-context Autoencoder (ICAE) to compress a long context into short compact memory slots. ICAE is first pretrained using both autoencoding and language modeling objectives on massive text data.
  arXiv  Detail & Related papers  (2023-07-13T17:59:21Z)
• Energy Transformer [64.22957136952725]
  Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. We propose a novel architecture, called the Energy Transformer (or ET for short), that uses a sequence of attention layers that are purposely designed to minimize a specifically engineered energy function.
  arXiv  Detail & Related papers  (2023-02-14T18:51:22Z)
• Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffs [62.91362897985057]
  An Intelligent IoT Environment (iIoTe) is comprised of heterogeneous devices that can collaboratively execute semi-autonomous IoT applications. This paper provides a state-of-the-art overview of these technologies and illustrates their functionality and performance, with special attention to the tradeoff among resources, latency, privacy and energy consumption.
  arXiv  Detail & Related papers  (2021-10-04T19:41:42Z)
• To Talk or to Work: Flexible Communication Compression for Energy Efficient Federated Learning over Heterogeneous Mobile Edge Devices [78.38046945665538]
  federated learning (FL) over massive mobile edge devices opens new horizons for numerous intelligent mobile applications. FL imposes huge communication and computation burdens on participating devices due to periodical global synchronization and continuous local training. We develop a convergence-guaranteed FL algorithm enabling flexible communication compression.
  arXiv  Detail & Related papers  (2020-12-22T02:54:18Z)
• Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications [77.00418462388525]
  This paper presents the first detailed experimental study of a mobile augmented reality (AR) client's energy consumption and the detection latency of executing Convolutional Neural Networks (CNN) based object detection. Our detailed measurements refine the energy analysis of mobile AR clients and reveal several interesting perspectives regarding the energy consumption of executing CNN-based object detection.
  arXiv  Detail & Related papers  (2020-11-26T00:32:07Z)
• TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices [71.68436132514542]
  We introduce the concept of attention condensers for building low-footprint, highly-efficient deep neural networks for on-device speech recognition on the edge. To illustrate its efficacy, we introduce TinySpeech, low-precision deep neural networks tailored for on-device speech recognition.
  arXiv  Detail & Related papers  (2020-08-10T16:34:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.