Can LLMs Generate User Stories and Assess Their Quality?

TL;DR

This paper investigates the capability of large language models to generate and evaluate user stories in requirements engineering, comparing their output to human-generated stories and assessing their potential to automate quality evaluation.

Contribution

It demonstrates that LLMs can generate user stories comparable to humans and reliably assess their semantic quality, offering a promising automation approach in requirements elicitation.

Findings

LLMs produce user stories similar to humans in coverage and style.

LLMs show lower diversity and creativity in generated stories.

LLMs can effectively evaluate semantic quality with clear criteria.

Abstract

Requirements elicitation is still one of the most challenging activities of the requirements engineering process due to the difficulty requirements analysts face in understanding and translating complex needs into concrete requirements. In addition, specifying high-quality requirements is crucial, as it can directly impact the quality of the software to be developed. Although automated tools allow for assessing the syntactic quality of requirements, evaluating semantic metrics (e.g., language clarity, internal consistency) remains a manual and time-consuming activity. This paper explores how LLMs can help automate requirements elicitation within agile frameworks, where requirements are defined as user stories (US). We used 10 state-of-the-art LLMs to investigate their ability to generate US automatically by emulating customer interviews. We evaluated the quality of US generated by LLMs, comparing it with the quality of US generated by humans (domain experts and students). We also explored whether and how LLMs can be used to automatically evaluate the semantic quality of US. Our results indicate that LLMs can generate US similar to humans in terms of coverage and stylistic quality, but exhibit lower diversity and creativity. Although LLM-generated US are generally comparable in quality to those created by humans, they tend to meet the acceptance quality criteria less frequently, regardless of the scale of the LLM model. Finally, LLMs can reliably assess the semantic quality of US when provided with clear evaluation criteria and have the potential to reduce human effort in large-scale assessments.