MODELS 2024
Sun 22 - Fri 27 September 2024 Linz, Austria
Thu 26 Sep 2024 16:27 - 16:45 at HS 1 - MDE and AI (1) Chair(s): Lola Burgueño

Current DSL environments lack smart editing facilities intended to enhance modeler productivity and cannot keep pace of current developments of integrated development environments based on AI. In this paper, we propose an approach to address this shortcoming through a recommender system specifically tailored for textual DSLs based on the fine-tuning of pre-trained language models. We identify three main tasks: identifier suggestion, line completion, and block completion, which we implement over the same fine-tuned model and we propose a workflow to apply these tasks to any textual DSL. We have evaluated our approach with different pre-trained models for three DSLs: Emfatic, Xtext and a DSL to specify domain entities, showing that the system performs well and provides accurate suggestions. We compare it against existing approaches in the feature name recommendation task showing that our system outperforms the alternatives. Moreover, we evaluate the inference time of our approach obtaining low latencies, which makes the system adequate for live assistance. Finally, we contribute a concrete recommender, named ModelMate, which implements the training, evaluation and inference steps of the workflow as well as providing integration into Eclipse-based textual editors.

Thu 26 Sep

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

15:45 - 17:30
MDE and AI (1)Technical Track / Tools and Demonstrations at HS 1
Chair(s): Lola Burgueño University of Malaga
15:45
18m
Talk
Text2VQL: Teaching a Model Query Language to Open-Source Language Models with ChatGPTFT
Technical Track
José Antonio Hernández López Linkoping University, Máté Földiák , Daniel Varro Linköping University / McGill University
16:06
18m
Talk
Enhancing Automata Learning with Statistical Machine Learning: A Network Security Case StudyPT
Technical Track
Negin Ayoughi University of Ottawa, Shiva Nejati University of Ottawa, Mehrdad Sabetzadeh University of Ottawa, Patricio Saavedra RabbitRun Technologies Inc
Pre-print
16:27
18m
Talk
ModelMate: A recommender for textual modeling languages based on pre-trained language modelsFT
Technical Track
Carlos Durá , José Antonio Hernández López Linkoping University, Jesús Sánchez Cuadrado Universidad de Murcia
DOI Authorizer link Pre-print
16:48
18m
Talk
DSL-Xpert: LLM-driven Generic DSL Code Generation
Tools and Demonstrations
Victor Lamas Universidade da Coruña, CITIC, Database Lab, Miguel Rodríguez Luaces Universidade da Coruña, Daniel Garcia-Gonzalez Universidade da Coruña, CITIC, Database Lab
17:09
18m
Talk
A RAG-based Feedback Tool to Augment UML Class Diagram Learning
Tools and Demonstrations
Pasquale Ardimento Università degli Studi di Bari, Mario Luca Bernardi University of Sannio, Marta Cimitile Unitelma Sapienza University, Michele Scalera University of Bari Aldo Moro - Department of Informatics
DOI