Large language models (LLMs) have shown remarkable progress in automated code
generation. Yet, incorporating LLM-based code generation into real-life
software projects poses challenges, as the generated code may contain errors in
API usage, class, data structure, or missing project-specific information. As
much of this project-specific context cannot fit into the prompts of LLMs, we
must find ways to allow the model to explore the project-level code context. To
this end, this paper puts forward a novel approach, termed ProCoder, which
iteratively refines the project-level code context for precise code generation,
guided by the compiler feedback. In particular, ProCoder first leverages
compiler techniques to identify a mismatch between the generated code and the
project's context. It then iteratively aligns and fixes the identified errors
using information extracted from the code repository. We integrate ProCoder
with two representative LLMs, i.e., GPT-3.5-Turbo and Code Llama (13B), and
apply it to Python code generation. Experimental results show that ProCoder
significantly improves the vanilla LLMs by over 80% in generating code
dependent on project context, and consistently outperforms the existing
retrieval-based code generation baselines.

该研究提出了一种名为 ProCoder 的新方法，通过迭代修复项目级代码上下文中的错误，引导编译器反馈，从而使生成的代码精确无误。实验结果表明，ProCoder 显著改进了基本的大语言模型在生成项目相关代码方面的性能，并持续优于现有的基于检索的代码生成基准。