Dániel Varró

On Inter-dataset Code Duplication and Data Leakage in Large Language Models

2024 · arXiv (Cornell University)

Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundational coding knowledge on large, general-purpose datasets during a pre-training phase, and subsequently refining …

Text2VQL: Teaching a Model Query Language to Open-Source Language Models with ChatGPT

2024

While large language models (LLMs) like ChatGPT has demonstrated impressive capabilities in addressing various software engineering tasks, their use in a model-driven engineering (MDE) context is still in an early stage. Since the technology is …