RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915455342477312 |
|---|---|
| author | Zhou, Changzhi Zhang, Xinyu Song, Dandan Chen, Xiancai Gu, Wanli Ma, Huipeng Tian, Yuhang Zhang, Mengdi Hu, Linmei |
| author_facet | Zhou, Changzhi Zhang, Xinyu Song, Dandan Chen, Xiancai Gu, Wanli Ma, Huipeng Tian, Yuhang Zhang, Mengdi Hu, Linmei |
| contents | Code generation has attracted increasing attention with the rise of Large Language Models (LLMs). Many studies have developed powerful code LLMs by synthesizing code-related instruction data and applying supervised fine-tuning. However, these methods are limited by teacher model distillation and ignore the potential of iterative refinement by self-generated code. In this paper, we propose Adaptive Critique Refinement (ACR), which enables the model to refine itself by self-generated code and external critique, rather than directly imitating the code responses of the teacher model. Concretely, ACR includes a composite scoring system with LLM-as-a-Judge to evaluate the quality of code responses and a selective critique strategy with LLM-as-a-Critic to critique self-generated low-quality code responses. We develop the RefineCoder series by iteratively applying ACR, achieving continuous performance improvement on multiple code generation benchmarks. Compared to the baselines of the same size, our proposed RefineCoder series can achieve comparable or even superior performance using less data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09183 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation Zhou, Changzhi Zhang, Xinyu Song, Dandan Chen, Xiancai Gu, Wanli Ma, Huipeng Tian, Yuhang Zhang, Mengdi Hu, Linmei Computation and Language Artificial Intelligence Code generation has attracted increasing attention with the rise of Large Language Models (LLMs). Many studies have developed powerful code LLMs by synthesizing code-related instruction data and applying supervised fine-tuning. However, these methods are limited by teacher model distillation and ignore the potential of iterative refinement by self-generated code. In this paper, we propose Adaptive Critique Refinement (ACR), which enables the model to refine itself by self-generated code and external critique, rather than directly imitating the code responses of the teacher model. Concretely, ACR includes a composite scoring system with LLM-as-a-Judge to evaluate the quality of code responses and a selective critique strategy with LLM-as-a-Critic to critique self-generated low-quality code responses. We develop the RefineCoder series by iteratively applying ACR, achieving continuous performance improvement on multiple code generation benchmarks. Compared to the baselines of the same size, our proposed RefineCoder series can achieve comparable or even superior performance using less data. |
| title | RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.09183 |