MODELS 2024
Sun 22 - Fri 27 September 2024 Linz, Austria
Thu 26 Sep 2024 16:48 - 17:06 at HS 1 - MDE and AI (1) Chair(s): Lola Burgueño

Nowadays, large language models (LLMs) are an extremely useful and fast tool to complement and help in many jobs and current problems. However, there are cases where a pretty specific vocabulary is used in which these models were not previously trained, leading to less satisfactory results. More specifically, these models are less effective when dealing with less-known or unpublished domain-specific languages (DSLs). Within this field, the automatic generation of code based on such languages, starting from natural language, would speed up the development times of any related project, as well as the understanding of such DSLs. Therefore, this paper presents a tool in which developers can perform what is known as semantic parsing. In other words, the developer can ask a pre-trained LLM to translate a natural language instruction into the vocabulary of the established DSL. Thus, by setting the DSL grammar as context (grammar prompting) and providing usage examples (few-shot learning), the LLM can quickly generate reliable domain-specific code, significantly improving the quality of life of the developers. A video demonstration of the tool is shown in the following link: https://zenodo.org/records/12610506.

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