no code implementations • 15 Jan 2024 • Fernando Vallecillos Ruiz, Anastasiia Grishina, Max Hort, Leon Moonen
We investigate whether this correction capability of Large Language Models (LLMs) extends to Automatic Program Repair (APR).
no code implementations • 5 Jul 2023 • Max Hort, Anastasiia Grishina, Leon Moonen
Large language models trained on source code can support a variety of software development tasks, such as code recommendation and program repair.
1 code implementation • 8 May 2023 • Anastasiia Grishina, Max Hort, Leon Moonen
These findings show that early layers can be used to obtain better results using the same resources, as well as to reduce resource usage during fine-tuning and inference.
no code implementations • 30 Apr 2023 • Anders Mølmen Høst, Pierre Lison, Leon Moonen
Knowledge graphs have shown promise for several cybersecurity tasks, such as vulnerability assessment and threat analysis.
no code implementations • 20 Apr 2023 • Vadim Liventsev, Anastasiia Grishina, Aki Härmä, Leon Moonen
Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human evaluation), but achieve a low or even zero accuracy as measured by unit tests due to small imperfections, such as the wrong input or output format.
no code implementations • 13 Mar 2023 • Sehrish Malik, Moeen Ali Naqvi, Leon Moonen
There is an increasing need to assess the correct behavior of self-adaptive and self-healing systems due to their adoption in critical and highly dynamic environments.
no code implementations • 28 Aug 2022 • Moeen Ali Naqvi, Sehrish Malik, Merve Astekin, Leon Moonen
In this paper, we propose CHESS, an approach for the systematic evaluation of self-adaptive and self-healing systems that builds on chaos engineering.
1 code implementation • 6 Feb 2022 • David Binkley, Leon Moonen, Sibren Isaacman
We also find that words are of greatest value in the datasets with a more homogeneous vocabulary.
2 code implementations • 19 Jul 2021 • Guru Prasad Bhandari, Amara Naseer, Leon Moonen
Data-driven research on the automated discovery and repair of security vulnerabilities in source code requires comprehensive datasets of real-life vulnerable code and their fixes.
no code implementations • 7 Jan 2021 • Moeen Ali Naqvi, Merve Astekin, Sehrish Malik, Leon Moonen
To help advance the state-of-the-art, we develop a research agenda for building self-healing software systems using AISs, identifying required foundations, and promising research directions.
no code implementations • 7 Sep 2020 • Carl Martin Rosenberg, Leon Moonen
(2) How does dimensionality reduction affect the quality of automated log clustering?