Document - The return of formal requirements engineering in the era of large language models

2024

Conference article Restricted

The return of formal requirements engineering in the era of large language models

Spoletini P., Ferrari A.

NLP Large language models Requirements Engineering Natural language processing Formal methods

Context and Motivation: Large Language Models (LLMs) have made remarkable advancements in emulating human linguistic capabilities, showing potential in executing various traditional software engineering tasks, including code generation. [Question/Problem] Despite their generally good performance, utilizing LLM-generated code raises legitimate concerns regarding its correctness and the assurances it can provide. [Principal Idea/Results] To address these concerns, we propose turning to formal requirements engineering—a practice currently predominantly used in developing complex systems where adherence to standards and accountability are required. [Contribution] In this vision paper, we discuss the integration of automatic formal requirements engineering techniques as a complement to LLM code generation. Additionally, we explore how LLMs can facilitate the broader acceptance of formal requirements, thus making the vision proposed in this paper realizable.

Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 14588, pp. 344-353. Winterthur, Switzerland, 8-11/04/2024

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:iris.cnr.it:20.500.14243/499625,
	title = {The return of formal requirements engineering in the era of large language models},
	author = {Spoletini P. and Ferrari A.},
	doi = {10.1007/978-3-031-57327-9_22},
	booktitle = {LECTURE NOTES IN COMPUTER SCIENCE, vol. 14588, pp. 344-353. Winterthur, Switzerland, 8-11/04/2024},
	year = {2024}
}