Probing with Precision: Probing Question Generation for Architectural Information Elicitation
Abstract
Software Requirements Specifications (SRS) often lack the necessary level of specificity required by software architects to make well-informed architectural decisions. This deficiency compels software architects to probe business analysts to collect more details pertinent to architectural requirements from the clients. In our previous work, we introduced Probing Question-flows (PQ-flows) that can assist business analysts to probe stakeholders and gather architecturally significant information for the creation of a more comprehensive SRS. Key limitations of our previous work were the manually created templatized PQ-flows and the mapping of PQ-flows to the software requirements based on standard Vector Space Model. In this study, we propose a Retrieval Augmented Generation (RAG) prompting framework to address these limitations. We conducted experiments using ChatGPT and Mistral-7B models. We present our findings utilizing human and automated evaluation metrics on a subset of the publicly available PUblic REquirements (PURE) dataset.CCS CONCEPTS• Software and its engineering → Requirements analysis; • Computing methodologies → Natural language generation; • Information systems → Information retrieval query processing; Question answering.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.