Document - Exploring LLMs’ ability to detect variability in requirements

2024

Conference article Restricted

Exploring LLMs’ ability to detect variability in requirements

Fantechi A., Gnesi S., Semini L.

Large language models Variability Natural Language Processing Requirements

In this paper, we address the question of whether general-purpose LLM-based tools may be useful for detecting requirements variability in Natural Language (NL) requirements documents. For this purpose, we conduct a preliminary exploratory study considering OpenAI chatGPT-3.5 and Microsoft Bing. Using two exemplar NL requirements documents, we compare the variability detection capability of the chatbots with that of experts and that of a rule-based NLP tool.

Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 14588, pp. 178-188. Winterthur, Switzerland, 8-11/04/2024

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:iris.cnr.it:20.500.14243/501088,
	title = {Exploring LLMs’ ability to detect variability in requirements},
	author = {Fantechi A. and Gnesi S. and Semini L.},
	doi = {10.1007/978-3-031-57327-9_11},
	booktitle = {LECTURE NOTES IN COMPUTER SCIENCE, vol. 14588, pp. 178-188. Winterthur, Switzerland, 8-11/04/2024},
	year = {2024}
}