Reproduce “Large Language Models (LLMs) for Requirements Engineering (RE): A Systematic Literature Review” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mohammad Amin Zadenoori, Jacek Dąbrowski, Waad Alhoshan, Liping Zhao, Alessio Ferrari
A systematic literature review on Large Language Models (LLMs) for Requirements Engineering (RE) identifies 74 studies published between 2023 and 2024, demonstrating a rapid shift towards LLM-driven approaches for tasks like elicitation and validation. The review highlights LLMs' distinct generative capabilities and their potential to re-center RE within the software development lifecycle.
Key insights
- The emergence of LLM4RE since 2023 represents a paradigm shift, focusing on more cognitively demanding and generative RE tasks like elicitation and validation, unlike earlier analytical NLP4RE research.
- LLMs have the potential to re-center RE in software engineering by facilitating automation across the development lifecycle, but current prompt engineering practices often lack systematic rigor and standardized guidelines.
- A significant reliance on private datasets and proprietary LLMs, coupled with a dominance of laboratory experiments over real-world evaluations, limits replicability and understanding of practical impact.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.