Generative AI for Requirements Engineering: A Systematic Literature Review

2024-09-10

arXiv.org

AI Summary

Generative AI faces critical challenges in requirements engineering—including insufficient coupling among explainability, reproducibility, and controllability, alongside a lack of ethical and safety governance—hindering its deployment in complex systems. To address this, we conduct a systematic literature review (SLR) of 105 peer-reviewed papers published between 2019 and 2024. Our analysis reveals, for the first time, strong co-occurrence (>35%) of these three attributes and identifies three primary challenge clusters: (1) inadequate technical attribute coupling (61.9%), (2) reproducibility bottlenecks induced by stochasticity (52.4%), and (3) insufficient governance coverage (<20%). Based on these findings, we propose an attribute-coupling–oriented architectural design paradigm tailored for generative AI in requirements engineering. Furthermore, we advocate establishing a standardized evaluation framework and a cross-domain collaborative governance system. This work provides both theoretical foundations and actionable implementation pathways for integrating generative AI into rigorous, trustworthy requirements engineering practices.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Context: Requirements engineering (RE) faces mounting challenges in handling increasingly complex software systems. The emergence of generative AI (GenAI) offers new opportunities and challenges in RE. Objective: This systematic literature review aims to analyze and synthesize current research on GenAI applications in RE, focusing on identifying research trends, methodologies, challenges, and future directions. Method: We conducted a comprehensive review of 105 articles published between 2019 and 2024 obtained from major academic databases, using a systematic methodology for paper selection, data extraction, and feature analysis. Results: Analysis revealed the following. (1) While GPT series models dominate current applications by 67.3% of studies, the existing architectures face technical challenges-interpretability (61.9%), reproducibility (52.4%), and controllability (47.6%), which demonstrate strong correlations (>35% co-occurrence). (2) Reproducibility is identified as a major concern by 52.4% of studies, which highlights challenges in achieving consistent results due to the stochastic nature and parameter sensitivity of GenAI. (3) Governance-related issues (e.g., ethics and security) form a distinct cluster of challenges that requires coordinated solutions, yet they are addressed by less than 20% of studies. Conclusions: While GenAI exhibits potential in RE, our findings reveal critical issues: (1) the high correlations among interpretability, reproducibility, and controllability imply the requirement for more specialized architectures that target interdependencies of these attributes. (2) The widespread concern about result consistency and reproducibility demands standardized evaluation frameworks. (3) The emergence of challenges related to interconnected governance demands comprehensive governance structures.

Problem

• Generative AI
• Software Engineering
• Ethical and Safety Issues

Innovation

• Generative AI in Requirements Engineering
• Ethical and Safety Considerations
• Specialized Models and Evaluation Systems