Leon Moonen
YOU?
Author Swipe
View article: Large Language Models: A Survey of Surveys
Large Language Models: A Survey of Surveys Open
This record accompanies the paper "Large Language Models: A Survey of Surveys" by Max Hort, Fernando Vallecillos-Ruiz, and Leon Moonen, currently under review. A PDF preprint is included in this record. The field of Large Language Models (…
View article: Replication package for "Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation"
Replication package for "Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation" Open
This repository contains the replication package for the paper "Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation" by Fernando Vallecillos Ruiz, Anastasiia Grishina, Max Hort a…
View article: The Impact of Fine-tuning Large Language Models on Automated Program Repair
The Impact of Fine-tuning Large Language Models on Automated Program Repair Open
Automated Program Repair (APR) uses various tools and techniques to help developers achieve functional and error-free code faster. In recent years, Large Language Models (LLMs) have gained popularity as components in APR tool chains becaus…
View article: Fully Autonomous Programming Using Iterative Multi-Agent Debugging with Large Language Models
Fully Autonomous Programming Using Iterative Multi-Agent Debugging with Large Language Models Open
Program synthesis with Large Language Models (LLMs) suffers from a “near-miss syndrome”: The generated code closely resembles a correct solution but fails unit tests due to minor errors. We address this with a multi-agent framework called …
View article: Self Healing of a Mixed Autonomy Traffic System Using Reinforcement Learning and Attention
Self Healing of a Mixed Autonomy Traffic System Using Reinforcement Learning and Attention Open
As urban traffic becomes increasingly complex with the integration of connected and autonomous vehicles alongside human-driven vehicles, there is a critical need for adaptive traffic management systems capable of self-healing in response t…
View article: A Comparative Study on Large Language Models for Log Parsing
A Comparative Study on Large Language Models for Log Parsing Open
Background: Log messages provide valuable information about the status of\nsoftware systems. This information is provided in an unstructured fashion and\nautomated approaches are applied to extract relevant parameters. To ease this\nproces…
View article: The Impact of Program Reduction on Automated Program Repair
The Impact of Program Reduction on Automated Program Repair Open
Correcting bugs using modern Automated Program Repair (APR) can be both time-consuming and resource-expensive. We describe a program repair approach that aims to improve the scalability of modern APR tools. The approach leverages program r…
View article: CVEfixes Dataset: Automatically Collected Vulnerabilities and Their Fixes from Open-Source Software
CVEfixes Dataset: Automatically Collected Vulnerabilities and Their Fixes from Open-Source Software Open
CVEfixes is a comprehensive vulnerability dataset that is automatically collected and curated from Common Vulnerabilities and Exposures (CVE) records in the public U.S. National Vulnerability Database (NVD). The goal is to support data-dri…
View article: Replication package for "Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation"
Replication package for "Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation" Open
<p>This repository contains the replication package for the paper “Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation” by Fernando Vallecillos Ruiz, Anastasiia…
View article: Extending the range of bugs that automated program repair can handle
Extending the range of bugs that automated program repair can handle Open
Modern automated program repair (APR) is well-tuned to finding and repairing bugs that introduce observable erroneous behavior to a program. However, a significant class of bugs does not lead to observable behavior (e.g., termination bugs …
View article: The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification
The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification Open
The use of modern Natural Language Processing (NLP) techniques has shown to\nbe beneficial for software engineering tasks, such as vulnerability detection\nand type inference. However, training deep NLP models requires significant\ncomputa…
View article: An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code
An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code Open
Context: Large language models trained on source code can support a variety of software development tasks, such as code recommendation and program repair. Large amounts of data for training such models benefit the models' performance. Howe…
View article: Fully Autonomous Programming with Large Language Models
Fully Autonomous Programming with Large Language Models Open
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 evaluat…
View article: Replication Package for "An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code"
Replication Package for "An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code" Open
This repository contains the replication package for the paper "An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code" by Max Hort, Anastasiia Grishina, and Leon Moonen, accepted for publication in th…
View article: Replication Package for "An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code"
Replication Package for "An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code" Open
This repository contains the replication package for the paper "An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code" by Max Hort, Anastasiia Grishina, and Leon Moonen, accepted for publication in th…
View article: An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code
An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code Open
Large language models trained on source code can support a variety of software development tasks, such as code recommendation and program repair. Large amounts of data for training such models benefit the models' performance. However, the …
View article: CHESS: A Framework for Evaluation of Self-Adaptive Systems Based on Chaos Engineering
CHESS: A Framework for Evaluation of Self-Adaptive Systems Based on Chaos Engineering Open
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. However, there is a lack of systematic evaluation methods for self-adap…
View article: Constructing a Knowledge Graph from Textual Descriptions of Software Vulnerabilities in the National Vulnerability Database
Constructing a Knowledge Graph from Textual Descriptions of Software Vulnerabilities in the National Vulnerability Database Open
Knowledge graphs have shown promise for several cybersecurity tasks, such as vulnerability assessment and threat analysis. In this work, we present a new method for constructing a vulnerability knowledge graph from information in the Natio…
View article: CHESS: A Framework for Evaluation of Self-adaptive Systems based on Chaos Engineering
CHESS: A Framework for Evaluation of Self-adaptive Systems based on Chaos Engineering Open
This repository contains the VM for CHESS: A Framework for Evaluation of Self-adaptive Systems based on Chaos Engineering This artifact was used in the paper "On Evaluating Self-Adaptive and Self-Healing Systems using Chaos Engineering", …
View article: Towards Extending the Range of Bugs That Automated Program Repair Can Handle
Towards Extending the Range of Bugs That Automated Program Repair Can Handle Open
Modern automated program repair (APR) is well-tuned to finding and repairing bugs that introduce observable erroneous behavior to a program. However, a significant class of bugs does not lead to such observable behavior (e.g., liveness/ter…
View article: On Evaluating Self-Adaptive and Self-Healing Systems using Chaos Engineering
On Evaluating Self-Adaptive and Self-Healing Systems using Chaos Engineering Open
With the growing adoption of self-adaptive systems in various domains, there is an increasing need for strategies to assess their correct behavior. In particular self-healing systems, which aim to provide resilience and fault-tolerance, of…
View article: Assessing the Impact of Execution Environment on Observation-Based Slicing
Assessing the Impact of Execution Environment on Observation-Based Slicing Open
Program slicing reduces a program to a smaller version that retains a chosen computation, referred to as a slicing criterion. One recent multi-lingual slicing approach, observation-based slicing (ORBS), speculatively deletes parts of the p…
View article: CVEfixes Dataset: Automatically Collected Vulnerabilities and Their Fixes from Open-Source Software
CVEfixes Dataset: Automatically Collected Vulnerabilities and Their Fixes from Open-Source Software Open
CVEfixes is a comprehensive vulnerability dataset that is automatically collected and curated from Common Vulnerabilities and Exposures (CVE) records in the public U.S. National Vulnerability Database (NVD). The goal is to support data-dri…
View article: Featherweight assisted vulnerability discovery
Featherweight assisted vulnerability discovery Open
Predicting vulnerable source code helps to focus attention on those parts of\nthe code that need to be examined with more scrutiny. Recent work proposed the\nuse of function names as semantic cues that can be learned by a deep neural\nnetw…
View article: Towards More Reliable Automated Program Repair by Integrating Static Analysis Techniques
Towards More Reliable Automated Program Repair by Integrating Static Analysis Techniques Open
A long-standing open challenge for automated program repair is the overfitting problem, which is caused by having insufficient or incomplete specifications to validate whether a generated patch is correct or not. Most available repair syst…
View article: CVEfixes: automated collection of vulnerabilities and their fixes from open-source software
CVEfixes: automated collection of vulnerabilities and their fixes from open-source software Open
Data-driven research on the automated discovery and repair of security\nvulnerabilities in source code requires comprehensive datasets of real-life\nvulnerable code and their fixes. To assist in such research, we propose a\nmethod to autom…
View article: CVEfixes Dataset: Automatically Collected Vulnerabilities and Their Fixes from Open-Source Software
CVEfixes Dataset: Automatically Collected Vulnerabilities and Their Fixes from Open-Source Software Open
CVEfixes is a comprehensive vulnerability dataset that is automatically collected and curated from Common Vulnerabilities and Exposures (CVE) records in the public U.S. National Vulnerability Database (NVD). The goal is to support data-dri…
View article: Adaptive Immunity for Software: Towards Autonomous Self-healing Systems
Adaptive Immunity for Software: Towards Autonomous Self-healing Systems Open
Testing and code reviews are known techniques to improve the quality and robustness of software. Unfortunately, the complexity of modern software systems makes it impossible to anticipate all possible problems that can occur at runtime, wh…
View article: On Adaptive Change Recommendation
On Adaptive Change Recommendation Open
As the complexity of a software system grows, it becomes harder for developers to be aware of all the dependencies between its artifacts (e.g., files or methods). Change impact analysis helps to overcome this challenge, by recommending rel…