Large Language Models Meet NL2Code: A Survey (2212.09420v2)

Abstract: The task of generating code from a natural language description, or NL2Code, is considered a pressing and significant challenge in code intelligence. Thanks to the rapid development of pre-training techniques, surging LLMs are being proposed for code, sparking the advances in NL2Code. To facilitate further research and applications in this field, in this paper, we present a comprehensive survey of 27 existing LLMs for NL2Code, and also review benchmarks and metrics. We provide an intuitive comparison of all existing models on the HumanEval benchmark. Through in-depth observation and analysis, we provide some insights and conclude that the key factors contributing to the success of LLMs for NL2Code are "Large Size, Premium Data, Expert Tuning". In addition, we discuss challenges and opportunities regarding the gap between models and humans. We also create a website https://nl2code.github.io to track the latest progress through crowd-sourcing. To the best of our knowledge, this is the first survey of LLMs for NL2Code, and we believe it will contribute to the ongoing development of the field.