Using reverse engineering to extract semantic representations from software systems is beneficial for understanding 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.