Towards Using LLMs in the Reverse Engineering of Software Systems to Object Constraint Language

TY - CONF

T1 - Towards Using LLMs in the Reverse Engineering of Software Systems to Object Constraint Language

AU - Siala, Hanan

AU - Lano, Kevin

PY - 2025/3/6

Y1 - 2025/3/6

N2 - 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 programtranslation. Yet, abstracting precise Object Constraint Language(OCL) specifications from source code using LLMs has notgained attention in reverse engineering approaches. In thispaper, we present a new reverse engineering approach, namedLLM4Models, to abstract OCL specifications from Java andPython programs, using LLMs.

AB - 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 programtranslation. Yet, abstracting precise Object Constraint Language(OCL) specifications from source code using LLMs has notgained attention in reverse engineering approaches. In thispaper, we present a new reverse engineering approach, namedLLM4Models, to abstract OCL specifications from Java andPython programs, using LLMs.

M3 - Paper

T2 - SANER 2025

Y2 - 4 March 2025 through 7 March 2025

ER -