Research directions for using LLM in software requirement engineering: a systematic review

Arshia Hemmat, Mohammadreza Sharbaf, Shekoufeh Kolahdouz Rahimi, Kevin Lano, Sobhan Yassipour Tehrani

Research output: Contribution to journalArticlepeer-review

4 Downloads (Pure)

Abstract

Natural Language Processing (NLP) and Large Language Models (LLMs) are transforming the landscape of software engineering, especially in the domain of requirement engineering. Despite significant advancements, there is a notable lack of comprehensive survey papers that provide a holistic view of the impact of these technologies on requirement engineering. This paper addresses this gap by reviewing the current state of NLP and LLMs in requirement engineering, highlighting their effects on improving requirement extraction, analysis, and specification. We analyze trends in software requirement engineering papers, noting an upward trajectory in the application of LLMs in software engineering tasks. This review underscores the critical role of requirement engineering in the software development lifecycle and emphasizes the transformative potential of LLMs in enhancing precision and reducing ambiguities in requirement specifications. Our findings indicate a growing interest and significant progress in leveraging LLMs for various software engineering tasks, particularly in requirement engineering. This paper aims to provide a foundation for future research and identify key challenges and opportunities in this evolving field.
Original languageEnglish
Article number1519437
Number of pages18
JournalFrontiers in Computer Science
Volume7
Issue number1519437.
DOIs
Publication statusPublished - 21 Mar 2025

Keywords

  • Software development
  • Requirement engineering
  • Large Language Models (LLMs)
  • Systematic literature review
  • Requirement specification

Cite this