AI-based Question Answering Assistance for Analyzing Natural-language Requirements

Abstract

By virtue of being prevalently written in natural language (NL), requirements are prone to various defects, e.g., inconsistency and incompleteness. As such, requirements are frequently subject to quality assurance processes. These processes, when carried out entirely manually, are tedious and may further overlook important quality issues due to time and budget pressures. In this paper, we propose QAssist -a questionanswering (QA) approach that provides automated assistance to stakeholders, including requirements engineers, during the analysis of NL requirements. Posing a question and getting an instant answer is beneficial in various quality-assurance scenarios, e.g., incompleteness detection. Answering requirementsrelated questions automatically is challenging since the scope of the search for answers can go beyond the given requirements specification. To that end, QAssist provides support for mining external domain-knowledge resources. Our work is one of the first initiatives to bring together QA and external domain knowledge for addressing requirements engineering challenges. We evaluate QAssist on a dataset covering three application domains and containing a total of 387 question-answer pairs. We experiment with state-of-the-art QA methods, based primarily on recent large-scale language models. In our empirical study, QAssist localizes the answer to a question to three passages within the requirements specification and within the external domainknowledge resource with an average recall of 90.1% and 96.5%, respectively. QAssist extracts the actual answer to the posed question with an average accuracy of 84.2%.

ARIA-QA: AI-Agent based Requirements Inspection and Analysis through Question Answering

“…In another research [1], an automated questionanswering (QA) approach is proposed that uses large-scale language models to extract compliance-related information from regulatory documents, achieving high effectiveness with 94% accuracy in locating relevant text passages and 91% accuracy in identifying correct answers. Another work [8] introduces QAssist, a question-answering (QA) approach that automates assistance for stakeholders, particularly requirements engineers, in analyzing natural language requirements, integrating external domain knowledge for comprehensive answers. Another research [2] proposes an AI-based automation for completeness checking of privacy policies, leveraging a conceptual model and completeness criteria derived from GDPR provisions.…”