Model transformation languages (MTLs) are domain-specific languages used to transform models conforming to a given metamodel into other models, including textual models such as source code. Developing correct model transformations in these languages is challenging and requires both language-specific and domain knowledge, creating a need for automated assistance and thus motivating the use of large language models (LLMs) for MTL code generation. However, due to the limited availability of training data and executable examples, LLM-generated MTL code is often not syntactically valid or semantically usable out of the box.

This paper presents LLM4MTLs, an automated workflow for improving the reliability of LLM-generated MTL code through systematic prompt construction that allows flexible selection of prompting strategy, together with an evaluation suite and an empirical evaluation. The workflow systematically explores prompt constructions combining few-shot prompting, grammar prompting, and helper methods inclusion, and evaluates them using both syntactic and semantic metrics. We construct an evaluation suite spanning four MTLs (ATL, ETL, QVTo, and the Reactions language) with executable reference scripts and manually written test suites, and evaluate across three LLMs. e find that few-shot prompting consistently improves syntactic quality across all four MTLs and yields notable gains in semantic correctness, although its ability to improve semantic correctness decreases for larger and more complex transformations, such as long ATL codes. Grammar prompting stabilizes code generation when combined with few-shot examples, but in isolation, it can be ineffective or even counterproductive for certain model–language combinations. Furthermore, including helper methods in the prompt as a complementary amplifier is beneficial. Finally, LLM Model choice influences syntactic correctness and similarity for certain MTLs, particularly ETL and QVTo, while its influence on semantic correction remains limited across all MTLs.