Sustainable Training of Code Language Models through Data Refinement

Informations projet

condenSE

N° de convention de subvention: 101151798

DOI

10.3030/101151798

Projet clôturé

Date de signature de la CE 6 Mars 2024

Date de début 1 Avril 2024

Date de fin 31 Mars 2026

Financé au titre de

• Marie Skłodowska-Curie Actions (MSCA)

Coût total

Aucune donnée

Contribution de l’UE

€ 210 911,04

Coordonné par

SIMULA RESEARCH LABORATORY AS
Norway

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Data Management Plan (1)

Data Management Plan

The Data Management Plan describes the data management life cycle for all data sets that will be collected, processed or generated by the action. It is a document describing what data will be collected, processed or generated and following what methodology and standards, whether and how this data will be shared and/or made open, and how it will be curated and preserved.

Publications

Conference proceedings (5)

Semantic-Preserving Transformations as Mutation Operators: A Study on Their Effectiveness in Defect Detection

Auteurs: Max Hort, Linas Vidziunas, Leon Moonen
Publié dans: 2025 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), 2025
Éditeur: IEEE
DOI: 10.1109/ICSTW64639.2025.10962512

The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models

Auteurs: Fernando Vallecillos Ruiz; Max Hort; Leon Moonen
Publié dans: Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering, 2025
DOI: 10.48550/ARXIV.2505.02931

The Impact of Fine-Tuning Large Language Models on Automated Program Repair

Auteurs: Roman Macháček, Anastasiia Grishina, Max Hort, Leon Moonen
Publié dans: 2025 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2025
Éditeur: IEEE
DOI: 10.1109/ICSME64153.2025.00042

Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforces

Auteurs: Max Hort, Leon Moonen
Publié dans: 2025 IEEE Conference on Software Testing, Verification and Validation (ICST), 2025
Éditeur: IEEE
DOI: 10.1109/ICST62969.2025.10988963

A Comparative Study on Large Language Models for Log Parsing

Auteurs: Merve Astekin; Max Hort; Leon Moonen
Publié dans: Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, 2024
DOI: 10.48550/ARXIV.2409.02474

Peer reviewed articles (2)

Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation

Auteurs: Fernando Vallecillos Ruiz, Anastasiia Grishina, Max Hort, Leon Moonen
Publié dans: ACM Transactions on Software Engineering and Methodology, 2025, ISSN 1049-331X
Éditeur: Association for Computing Machinery (ACM)
DOI: 10.1145/3771922

Fairst: A Novel Approach for Machine Learning Bias Repair Through Latent Sensitive Attribute Translation

Auteurs: Carmen Meinson; Max Hort; Federica Sarro
Publié dans: Information and Software Technology, 2025, ISSN 1873-6025
Éditeur: Elsevier B.V.
DOI: 10.1016/J.INFSOF.2025.107900