76 citations · 111 across the 19 of their papers we have counts for
19 papers
Balancing Usefulness and Naturalness: An LLM-based Curation Pipeline for Code Review Comments
Oussama Ben Sghaier, Martin Weyssow, Houari Sahraoui
Code review is a cornerstone of software development, where reviewers provide feedback through written comments to ensure code quality, maintainability, and correctness. The effect…
Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
Yikun Li, Ngoc Tan Bui, Ting Zhang +16
Automated vulnerability detection research has made substantial progress, yet its real-world impact remains limited. Prior work found that current vulnerability datasets suffer fro…
An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
Xin Zhou, Kisub Kim, Ting Zhang +6
Large Language Models (LLMs) and other automated techniques have been increasingly used to support software developers by generating software artifacts such as code snippets, patch…
Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents
Ratnadira Widyasari, Martin Weyssow, Ivana Clairine Irsan +6
Detecting vulnerabilities in source code remains a critical yet challenging task, especially when benign and vulnerable functions share significant similarities. In this work, we i…
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
Martin Weyssow, Chengran Yang, Junkai Chen +12
Large language models (LLMs) have shown promising performance in software vulnerability detection, yet their reasoning capabilities remain unreliable. We propose R2Vul, a method th…
Artificial Intelligence for Software Architecture: Literature Review and the Road Ahead
Alessio Bucaioni, Martin Weyssow, Junda He +2
Artificial intelligence is increasingly applied across software engineering, yet its explicit role in software architecture remains insufficiently understood. Architectural practic…
Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection
Ting Zhang, Chengran Yang, Yindu Su +8
Recent advancements in generative AI have led to the widespread adoption of large language models (LLMs) in software engineering, addressing numerous long-standing challenges. Howe…
LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks
Xin Zhou, Martin Weyssow, Ratnadira Widyasari +7
Large Language Models (LLMs) are widely utilized in software engineering (SE) tasks, such as code generation and automated program repair. However, their reliance on extensive and…
Harnessing Large Language Models for Curated Code Reviews
Oussama Ben Sghaier, Martin Weyssow, Houari Sahraoui
In code review, generating structured and relevant comments is crucial for identifying code issues and facilitating accurate code changes that ensure an efficient code review proce…
A Functional Software Reference Architecture for LLM-Integrated Systems
Alessio Bucaioni, Martin Weyssow, Junda He +2
The integration of large language models into software systems is transforming capabilities such as natural language understanding, decision-making, and autonomous task execution.…
CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics
Yikun Li, Ting Zhang, Ratnadira Widyasari +13
Accurate identification of software vulnerabilities is crucial for system integrity. Vulnerability datasets, often derived from the National Vulnerability Database (NVD) or directl…
CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences
Martin Weyssow, Aton Kamanda, Xin Zhou +1
Evaluating the alignment of large language models (LLMs) with user-defined coding preferences is a challenging endeavour that requires a deep assessment of LLMs' outputs. Existing…
CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code
Martin Weyssow, Claudio Di Sipio, Davide Di Ruscio +1
Motivated by recent work on lifelong learning applications for language models (LMs) of code, we introduce CodeLL, a lifelong learning dataset focused on code changes. Our contribu…
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models
Martin Weyssow, Xin Zhou, Kisub Kim +2
Large language models (LLMs) demonstrate impressive capabilities to generate accurate code snippets given natural language intents in a zero-shot manner, i.e., without the need for…
On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code
Martin Weyssow, Xin Zhou, Kisub Kim +2
Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general know…
AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models
José Antonio Hernández López, Martin Weyssow, Jesús Sánchez Cuadrado +1
The objective of pre-trained language models is to learn contextual representations of textual data. Pre-trained language models have become mainstream in natural language processi…
Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning
Martin Weyssow, Houari Sahraoui, Bang Liu
The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approaches based on state-of-the-art model archi…
Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models
Martin Weyssow, Houari Sahraoui, Eugene Syriani
The design of conceptually sound metamodels that embody proper semantics in relation to the application domain is particularly tedious in Model-Driven Engineering. As metamodels de…
Combining Code Embedding with Static Analysis for Function-Call Completion
M. Weyssow, H. Sahraoui, B. Frénay +1
Code completion is an important feature of integrated development environments (IDEs). It allows developers to produce code faster, especially novice ones who are not fully familia…