Prompt Engineering Guidelines for Using Large Language Models in Requirements Engineering

TL;DR

This paper explores how prompt engineering guidelines can be applied to improve the use of Large Language Models in Requirements Engineering, addressing a gap in domain-specific guidance and proposing a mapping to enhance effectiveness.

Contribution

It systematically reviews existing prompt engineering guidelines, interviews RE experts, and develops a mapping to address the shortage of domain-specific guidance for RE activities.

Findings

Shortage of prompt engineering guidelines for RE

Expert insights on guideline advantages and limitations

Proposed mapping to improve LLM usage in RE

Abstract

The rapid emergence of generative AI models like Large Language Models (LLMs) has demonstrated its utility across various activities, including within Requirements Engineering (RE). Ensuring the quality and accuracy of LLM-generated output is critical, with prompt engineering serving as a key technique to guide model responses. However, existing literature provides limited guidance on how prompt engineering can be leveraged, specifically for RE activities. The objective of this study is to explore the applicability of existing prompt engineering guidelines for the effective usage of LLMs within RE. To achieve this goal, we began by conducting a systematic review of primary literature to compile a non-exhaustive list of prompt engineering guidelines. Then, we conducted interviews with RE experts to present the extracted guidelines and gain insights on the advantages and limitations of their application within RE. Our literature review indicates a shortage of prompt engineering guidelines for domain-specific activities, specifically for RE. Our proposed mapping contributes to addressing this shortage. We conclude our study by identifying an important future line of research within this field.