Towards Energy-aware Requirements Dependency Classification: Knowledge-Graph vs. Vector-Retrieval Augmented Inference with SLMs

TL;DR

This paper compares knowledge graph and vector retrieval methods to improve energy-efficient requirement conflict detection using small language models, balancing accuracy and environmental impact.

Contribution

It introduces an empirical evaluation of energy-aware retrieval strategies for requirement classification with SLMs, emphasizing sustainability in requirements engineering.

Findings

Knowledge graph retrieval outperforms semantic retrieval in conflict detection accuracy.

Structured retrieval methods reduce energy consumption and carbon emissions.

The framework balances predictive performance with environmental sustainability.

Abstract

The continuous evolution of system specifications necessitates frequent evaluation of conflicting requirements, a process that is traditionally labour intensive. Although large language models (LLMs) have demonstrated significant potential for automating this detection, their massive computational requirements often result in excessive energy waste. Consequently, there is a growing need to transition toward Small Language Models (SLMs) and energy aware architectures for sustainable Requirements Engineering. This study proposes and empirically evaluates an energy aware framework that compares Knowledge Graph-based Retrieval (KGR) with Vector-based Semantic Retrieval (VSR) to enhance SLM-based inference at the 7B to 8B parameter scale. By leveraging structured graph traversal and high dimensional semantic mapping, we extract candidate requirements, which are then classified as conflicting or neutral by an inference engine. We evaluate these retrieval enhanced strategies across Zero-Shot, Few-Shot, and Chain of Thoughts prompting methods. Using a three-pillar sustainability framework measuring energy consumption (Wh), latency (s), and carbon emissions (gCO2eq) alongside standard accuracy metrics (F1 Score), this research provides a first systematic empirical evaluation and trade off analysis between predictive performance and environmental impact. Our findings highlight the effectiveness of structured versus semantic retrieval in detecting requirement conflicts, offering a reproducible, sustainability aware architecture for energy efficient requirement engineering.