Previous work has investigated the adequacy of LLMs to detect inconsistencies in requirements documents, but has also shown their limitations with real case studies. In this paper, we propose a hybrid approach, which exploits traditional clustering techniques to help LLMs focus on potential inconsistencies. The approach was evaluated using a large security requirements document from the RE Open Data Initiative, with injected inconsistencies. Results show that combining LLM-based detection with rule-based clustering enhances both precision and recall.
Combining Established and Emerging Techniques to Detect Inconsistencies in Requirements
Fantechi A.;Semini L.
2025-01-01
Abstract
Previous work has investigated the adequacy of LLMs to detect inconsistencies in requirements documents, but has also shown their limitations with real case studies. In this paper, we propose a hybrid approach, which exploits traditional clustering techniques to help LLMs focus on potential inconsistencies. The approach was evaluated using a large security requirements document from the RE Open Data Initiative, with injected inconsistencies. Results show that combining LLM-based detection with rule-based clustering enhances both precision and recall.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
