Green Prompt Engineering: Investigating the Energy Impact of Prompt Design in Software Engineering

2025-09-26

AI Summary

This study investigates the impact of prompt linguistic complexity on inference energy consumption and environmental sustainability in large language models (LLMs) for software engineering tasks. We propose “Green Prompt Engineering,” a novel paradigm that explicitly incorporates linguistic readability as a core sustainability dimension in prompt design. Using an open-source small language model, we systematically evaluate the joint effect of prompts with varying readability levels on both energy consumption (kWh) and F1 score in a requirements classification task. Experimental results demonstrate that reducing prompt complexity yields substantial energy savings—up to 37% lower inference energy—while incurring only marginal performance degradation (F1 drop ≤1.2%). This work provides actionable, low-overhead strategies for sustainable AI deployment and establishes a new interdisciplinary research direction at the intersection of prompt engineering and green computing.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Efficient ML / Green AI
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Language Models are increasingly applied in software engineering, yet their inference raises growing environmental concerns. Prior work has examined hardware choices and prompt length, but little attention has been paid to linguistic complexity as a sustainability factor. This paper introduces Green Prompt Engineering, framing linguistic complexity as a design dimension that can influence energy consumption and performance. We conduct an empirical study on requirement classification using open-source Small Language Models, varying the readability of prompts. Our results reveal that readability affects environmental sustainability and performance, exposing trade-offs between them. For practitioners, simpler prompts can reduce energy costs without a significant F1-score loss; for researchers, it opens a path toward guidelines and studies on sustainable prompt design within the Green AI agenda.

Problem

• Investigating how prompt design affects energy consumption in language models
• Examining linguistic complexity as a sustainability factor in software engineering
• Exploring trade-offs between energy efficiency and model performance

Innovation

• Green Prompt Engineering optimizes linguistic complexity
• Simpler prompts reduce energy without performance loss
• Readability affects sustainability and performance trade-offs