ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913865530343424 |
|---|---|
| author | Ren, Houxing Zhan, Mingjie Wu, Zhongyuan Zhou, Aojun Pan, Junting Li, Hongsheng |
| author_facet | Ren, Houxing Zhan, Mingjie Wu, Zhongyuan Zhou, Aojun Pan, Junting Li, Hongsheng |
| contents | Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPL-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17057 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation Ren, Houxing Zhan, Mingjie Wu, Zhongyuan Zhou, Aojun Pan, Junting Li, Hongsheng Computation and Language Artificial Intelligence Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPL-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder. |
| title | ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.17057 |