Similar Items: A multi-language perspective on the robustness of LLM code generation
- From brittle to robust: Improving LLM annotations for SE optimization
- Identifying performance-sensitive configurations in software systems with LLM-based agents
- Meta-enhanced code: leveraging structural and functional features for precise cross-modal code search
- Machine learning, deep learning, or large language models: An empirical study on multi-label requirements classification
- Exploring and improving knowledge distillation for pre-trained code models
- Effective Fine-tuning for Low-resource Languages: A Case Study of Cangjie