mlsanityData to 14 Oct 2026

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

arXiv 2607.22568 ↗First posted 31 May 2026cs.AI cs.NIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 23 references that are in the map. First posted on arXiv 31 May 2026.

Builds on

11 of 23 references.

References · 11

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  6. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  7. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  8. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  9. 2019Green AIcited by 627
  10. 2022Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Modelcited by 265
  11. 2020Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Modelscited by 169

Built on by

Not cited yet.