4 papers
Imperfect Visual Verification for Code Edition : A Case Study on TikZ
Charly Reux, Mathieu Acher, Djamel Eddine Khelladi +2
LLMs have significantly advanced code generation, enabling the synthesis of functional programs. While recent systems achieve strong performance on many coding benchmarks, tasks in…
Did You Forkget It? Detecting One-Day Vulnerabilities in Open-source ForksWith Global History Analysis
Romain Lefeuvre, Charly Reux, Stefano Zacchiroli +2
Tracking vulnerabilities inherited from third-party open-source software is a well-known challenge, often addressed by tracing the threads of dependency information. However, vulne…
LLM Code Customization with Visual Results: A Benchmark on TikZ
Charly Reux, Mathieu Acher, Djamel Eddine Khelladi +2
With the rise of AI-based code generation, customizing existing code out of natural language instructions to modify visual results -such as figures or images -has become possible,…
Unify and Triumph: Polyglot, Diverse, and Self-Consistent Generation of Unit Tests with LLMs
Djamel Eddine Khelladi, Charly Reux, Mathieu Acher
Large language model (LLM)-based test generation has gained attention in software engineering, yet most studies evaluate LLMs' ability to generate unit tests in a single attempt fo…