Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909220780113920 |
|---|---|
| author | Bi, Zhangqian Wan, Yao Wang, Zheng Zhang, Hongyu Guan, Batu Lu, Fangxin Zhang, Zili Sui, Yulei Jin, Hai Shi, Xuanhua |
| author_facet | Bi, Zhangqian Wan, Yao Wang, Zheng Zhang, Hongyu Guan, Batu Lu, Fangxin Zhang, Zili Sui, Yulei Jin, Hai Shi, Xuanhua |
| contents | Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-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. We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches 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 CoCoGen 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 CoCoGen significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16792 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback Bi, Zhangqian Wan, Yao Wang, Zheng Zhang, Hongyu Guan, Batu Lu, Fangxin Zhang, Zili Sui, Yulei Jin, Hai Shi, Xuanhua Computation and Language Software Engineering Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-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. We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches 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 CoCoGen 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 CoCoGen significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines. |
| title | Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback |
| topic | Computation and Language Software Engineering |
| url | https://arxiv.org/abs/2403.16792 |