TY - JOUR
T1 - Research directions for using LLM in software requirement engineering
T2 - a systematic review
AU - Hemmat, Arshia
AU - Sharbaf, Mohammadreza
AU - Kolahdouz-Rahimi, Shekoufeh
AU - Lano, Kevin
AU - Tehrani, Sobhan Y.
N1 - Publisher Copyright:
Copyright © 2025 Hemmat, Sharbaf, Kolahdouz-Rahimi, Lano and Tehrani.
PY - 2025
Y1 - 2025
N2 - Introduction: 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. Methods: We analyze trends in software requirement engineering papers, focusing on the application of NLP and LLMs. The review highlights their effects on improving requirement extraction, analysis, and specification, and identifies key patterns in the adoption of these technologies. Results: The findings reveal an upward trajectory in the use of LLMs for software engineering tasks, particularly in requirement engineering. The 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. Discussion: This paper identifies a growing interest and significant progress in leveraging LLMs for various software engineering tasks, particularly in requirement engineering. It provides a foundation for future research and highlights key challenges and opportunities in this evolving field.
AB - Introduction: 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. Methods: We analyze trends in software requirement engineering papers, focusing on the application of NLP and LLMs. The review highlights their effects on improving requirement extraction, analysis, and specification, and identifies key patterns in the adoption of these technologies. Results: The findings reveal an upward trajectory in the use of LLMs for software engineering tasks, particularly in requirement engineering. The 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. Discussion: This paper identifies a growing interest and significant progress in leveraging LLMs for various software engineering tasks, particularly in requirement engineering. It provides a foundation for future research and highlights key challenges and opportunities in this evolving field.
KW - Large Language Models (LLMs)
KW - requirement engineering
KW - requirement specification
KW - software development
KW - systematic literature review
UR - http://www.scopus.com/inward/record.url?scp=105001821240&partnerID=8YFLogxK
U2 - 10.3389/fcomp.2025.1519437
DO - 10.3389/fcomp.2025.1519437
M3 - Article
AN - SCOPUS:105001821240
SN - 2624-9898
VL - 7
JO - Frontiers in Computer Science
JF - Frontiers in Computer Science
M1 - 1519437
ER -