Towards using Few-Shot Prompt Learning for Automating Model Completion

2022/12/07 by Meriem Ben Chaaben, Chaaben, Meriem Ben, Loli Burgueño +3 · 6 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Software Engineering (cs.SE) #Software Engineering Research #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2212.03404

openalex publication_date 2022/12/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Large Language Models for Software Engineering Diagrams: A Systematic Review of UML and ER modelling
• Mind the Ethics! The Overlooked Ethical Dimensions of GenAI in Software Modeling Education
• SHERPA: A Model-Driven Framework for Large Language Model Execution
• MCeT: Behavioral Model Correctness Evaluation using Large Language Models
• Vibe Modeling: Challenges and Opportunities
• Investigating the Role of LLMs Hyperparameter Tuning and Prompt Engineering to Support Domain Modeling

Related

• On the Utility of Domain Modeling Assistance with Large Language Models
• Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models
• Making Pre-trained Language Models Better Few-shot Learners
• On the Utility of Domain-Adjacent Fine-Tuned Model Ensembles for Few-shot Problems
• Continued Pretraining for Better Zero- and Few-Shot Promptability