Many organizations rely on software systems to accomplish their daily operations. Over time, these systems require maintenance and need to evolve to meet new requirements and stakeholder needs. Visual representations and textual abstractions are important to support the understanding of these systems for their maintenance and evolution. Reverse engineering is used to generate such representations and software models by abstracting various types of diagrams from code bases, and Model-Driven Engineering (MDE) provides a rigorous means of facilitating the reverse engineering process, enabling the generation of formal visual and textual models with a precise semantic alignment to the source code. Large language models (LLMs) are increasingly used in various fields, including software engineering. Yet, they have rarely been used to abstract software models from source code. In this paper, we present a new Model-Driven Reverse Engineering (MDRE) approach for abstracting Unified Modeling Language (UML) and Object Constraint Language (OCL) representations from software systems for understanding and documenting them. To improve the usability and scope of MDRE, we use LLMs to abstract UML class diagrams and OCL specifications from Java and Python programs. Case studies are conducted to evaluate the proposed approach and to encourage maintainers to leverage LLMs in the reverse engineering process, thereby improving their understanding and maintenance of Java- and Python-based systems.

Using reverse engineering to extract semantic representations from software systems is beneficial for the understanding of these systems, and can facilitate their maintenance and evolution. In particular, extracting semantically-precise specifications from systems is useful for re-engineering of systems to functionally-equivalent versions in different programming languages. Large language models (LLMs) are a type of machine learning (ML) technique that has been utilized in various domains, including software engineering and program translation. Yet, abstracting precise Object Constraint Language (OCL) specifications from source code using LLMs has not gained attention in reverse engineering approaches. In this paper, we present a new reverse engineering approach, named LLM4Models, to abstract OCL specifications from Java and Python programs, using LLMs.

Abstract The porting or translation of software applications from one programming language to another is a common requirement of organisations that utilise software, and the increasing number and diversity of programming languages makes this capability as relevant today as in previous decades. Several approaches have been used to address this challenge, including machine learning and the manual definition of direct language-to-language translation rules, however the accuracy of these approaches remains unsatisfactory. In this paper we describe a new approach to program translation using model-driven engineering techniques: reverse-engineering source programs into specifications in the UML and OCL formalisms, and then forward-engineering the specifications to the required target language. This approach can provide assurance of semantic preservation, and additionally has the advantage of extracting precise specifications of software from code. We provide an evaluation based on a comprehensive dataset of examples, including industrial cases, and compare our results to those of other approaches and tools. Our specific contributions are: (1) Reverse-engineering source programs to detailedsemantic modelsof software behaviour, to enable semantically-correct translations and reduce re-testing costs; (2) Program abstraction processes defined by precise and explicit rules, which can be edited and configured by users; (3) A set of reusable OCL library components appropriate for representing program semantics, and which can also be used for OCL specification of new applications; (4) A systematic procedure for building program abstractors based on language grammars and semantics.