Exploring the Use of LLMs for Requirements Specification in an IT Consulting Company

July 25, 2025 Β· Declared Dead Β· πŸ› IEEE International Requirements Engineering Conference

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Liliana Pasquale, Azzurra Ragone, Emanuele Piemontese, Armin Amiri Darban arXiv ID 2507.19113 Category cs.SE: Software Engineering Citations 1 Venue IEEE International Requirements Engineering Conference Last Checked 5 months ago
Abstract
In practice, requirements specification remains a critical challenge. The knowledge necessary to generate a specification can often be fragmented across diverse sources (e.g., meeting minutes, emails, and high-level product descriptions), making the process cumbersome and time-consuming. In this paper, we report our experience using large language models (LLMs) in an IT consulting company to automate the requirements specification process. In this company, requirements are specified using a Functional Design Specification (FDS), a document that outlines the functional requirements and features of a system, application, or process. We provide LLMs with a summary of the requirements elicitation documents and FDS templates, prompting them to generate Epic FDS (including high-level product descriptions) and user stories, which are subsequently compiled into a complete FDS document. We compared the correctness and quality of the FDS generated by three state-of-the-art LLMs against those produced by human analysts. Our results show that LLMs can help automate and standardize the requirements specification, reducing time and human effort. However, the quality of LLM-generated FDS highly depends on inputs and often requires human revision. Thus, we advocate for a synergistic approach in which an LLM serves as an effective drafting tool while human analysts provide the critical contextual and technical oversight necessary for high-quality requirements engineering (RE) documentation.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted