Few-shot prompting improves syntactic validity of LLM-generated code across ATL, ETL, QVTo, and Reactions, but semantic correctness gains remain uneven and language-dependent.
Proceedings of the 25th
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Surveys reveal students prefer socially relevant domains for motivation in software modelling education and value choice in selection, contrary to educator assumptions, recommending student-centered domain selection.
citing papers explorer
-
LLM4MTLs: Automated Generation and Empirical Evaluation of Model Transformation Languages
Few-shot prompting improves syntactic validity of LLM-generated code across ATL, ETL, QVTo, and Reactions, but semantic correctness gains remain uneven and language-dependent.
-
Domain Diversity, Motivation, Inclusion, and Feedback in Software Modelling Education
Surveys reveal students prefer socially relevant domains for motivation in software modelling education and value choice in selection, contrary to educator assumptions, recommending student-centered domain selection.