cs.SE · 2605.11045 Copy arXiv ID · May 11, 2026 Save Read, Extract, Classify: A Tool for Smarter Requirements Engineering Authors: Paheli Bhattacharya , Manojit Chakraborty , Santhosh Kumar Arumugam , Rishabh Gupta
Organizations: Bosch Research and Technology Centre, Bangalore, India
Abstract This paper presents the ReXCL tool, which automates the extraction and classification processes in requirements engineering, enhancing the software development life-cycle. The tool features two main modules: Extraction, which processes raw requirement documents into a predefined schema using heuristics and predictive modeling, and Classification, which assigns class labels to requirements using adaptive fine-tuning of encoder-based models. The final output can be exported to external requirement engineering tools. Performance evaluations indicate that ReXCL significantly improves efficiency and accuracy in managing requirements, marking a novel approach to automating the schematization of semi-structured requirement documents.
Explore similar work Jul 5, 2026 · Pavithra PM Nair, Preethu Rose Anish Requirements Engineering Regulation
Apr 24, 2026 · Anna Arnaudo, Riccardo Coppola, Maurizio Morisio +4 Requirements Engineering Context-Aware Sub-Goal Generation
Jun 15, 2026 · Hazem Ayman, Menna Sedik, Kareem Mostafa +3 Requirements Engineering Test Generation
Jul 5, 2026 · cs.SE J/K move · Enter open · S save
Pavithra PM Nair, Preethu Rose Anish
Tata Consultancy Services
Ensuring software compliance with regulations such as the General Data Protection Regulation (GDPR) and the Artificial Intelligence Act (EU AI Act) poses a significant challenge, as requirements engineers must translate complex legal text into actionable software requirements - a process that remains largely manual and error-prone in practice. We present an automated regulation-to-requirements pipeline that identifies requirement-bearing clauses in regulatory documents and derives system-agnostic software requirements, accompanied by plain-language explanations, traceable to their legal sources. We evaluate the pipeline on the full clause sets of the GDPR (398 clauses) and the EU AI Act (574 clauses). For requirement-bearing clause identification, the approach achieves macro-averaged F1 scores of 0.82 and 0.78, respectively, outperforming a SetFit-based baseline. Human evaluation shows high completeness (4.60 and 4.45) and correctness (3.74 and 3.54) of derived requirements, while explanation clarity scores are near-ceiling (4.92 and 4.94) on a 1-5 scale. We implement the approach in Reg2Req, a publicly released tool that further supports requirement classification, use case seeding, cross-reference analysis, definition indexing, and a traceability matrix to operationalize regulatory compliance in practice. A user study with 25 practitioners shows that the plain-language explanations significantly improve comprehension of derived requirements and confidence in acting on them (p < 0.001), and that all participants would use Reg2Req as a starting point for deriving software requirements from a regulation.