Number of papers: 1
- Authors: Olausson, Theo X and Inala, Jeevana Priya and Wang, Chenglong and Gao, Jianfeng and Solar-Lezama, Armando
- Abstract: Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair---in which the model debugs and repairs its own code---has recently become a popular way to boost performance in these settings. However, despite its increasing popularity, existing studies of self-repair have been limited in scope; in many settings, its efficacy thus remains poorly understood. In this paper, we analyze Code Llama, GPT-3.5 and GPT-4's ability to perfo...
- Link: Read Paper
- Labels: code generation, program repair