2026-04-14T03:20:23Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4391732026-01-21T09:25:44Zcom_2072_1033col_2072_452950

urn:hdl:2117/439173 Leveraging requirements elicitation through software requirement patterns and LLMs Franch Gutiérrez, Javier Gnesi, Stefania Paccosi, Federico Quer, Carme Semini, Laura Àrees temàtiques de la UPC::Informàtica::Enginyeria del software Requirement patterns Large language models LLM Requirements elicitation Prompts Software requirement patterns (SRPs) is one of the many techniques that contribute to requirements elicitation. At this respect, the emergence of large language models (LLMs) opens the door to cost-effective strategies to create and use SRPs. Still, the stochastic nature of LLMs threatens the inherent quality of requirements reuse and consequently, that of the elicitation process. [Question/problem] In this scientific evaluation paper, we investigate whether and how LLMs can be used in order to create an SRP catalogue and elicit requirements from it. [Principal ideas/results] SRPs can be effectively extracted by querying an LLM through appropriate prompts, but still expert assessment is key in order to deliver the best results. LLM-driven generation of questions to stakeholders for eliciting requirements from these SRPs is feasible but suffers from deficiencies such as excessive number of repetitions and out of scope requirements. [Contribution] We show that (1) LLMs can be embedded into the requirements elicitation process through a pattern instantiation-based strategy, but at the same time (2) the current state of LLM technologies requires expert assessment at a large extent. This paper has been partially funded by the Spanish Ministerio de Ciencia e Innovación under project/funding scheme PID2020-117191RBI00/AEI/10.13039/501100011033, by the Italian MIUR, under project PRIN 2022 STENDHAL and PNRR Project Securing sOftware Platforms. Postprint (published version) 2025 Conference report https://link.springer.com/chapter/10.1007/978-3-031-88531-0_19 info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-117191RB-I00/ES/DESARROLLO, OPERATIVA Y GOBERNANZA DE DATOS PARA SISTEMAS SOFTWARE BASADOS EN APRENDIZAJE AUTOMATICO/ Restricted access - publisher's policy Springer