Towards using Few-Shot Prompt Learning for Automating Model Completion
This addresses the challenge of scarce data in domain modeling for practitioners, though it appears incremental as it applies existing few-shot techniques to a specific domain.
The paper tackled the problem of automating model completion in domain modeling by using few-shot prompt learning with large language models, eliminating the need for extensive training data, and initial evaluation showed it is effective for completing static and dynamic domain diagrams.
We propose a simple yet a novel approach to improve completion in domain modeling activities. Our approach exploits the power of large language models by using few-shot prompt learning without the need to train or fine-tune those models with large datasets that are scarce in this field. We implemented our approach and tested it on the completion of static and dynamic domain diagrams. Our initial evaluation shows that such an approach is effective and can be integrated in different ways during the modeling activities.