OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910774701588480 |
|---|---|
| author | Zheng, Tianyu Zhang, Ge Shen, Tianhao Liu, Xueling Lin, Bill Yuchen Fu, Jie Chen, Wenhu Yue, Xiang |
| author_facet | Zheng, Tianyu Zhang, Ge Shen, Tianhao Liu, Xueling Lin, Bill Yuchen Fu, Jie Chen, Wenhu Yue, Xiang |
| contents | The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance. Notably, OpenCodeInterpreter-33B achieves an accuracy of 83.2 (76.4) on the average (and plus versions) of HumanEval and MBPP, closely rivaling GPT-4's 84.2 (76.2) and further elevates to 91.6 (84.6) with synthesized human feedback from GPT-4. OpenCodeInterpreter brings the gap between open-source code generation models and proprietary systems like GPT-4 Code Interpreter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14658 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement Zheng, Tianyu Zhang, Ge Shen, Tianhao Liu, Xueling Lin, Bill Yuchen Fu, Jie Chen, Wenhu Yue, Xiang Software Engineering Artificial Intelligence Computation and Language The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance. Notably, OpenCodeInterpreter-33B achieves an accuracy of 83.2 (76.4) on the average (and plus versions) of HumanEval and MBPP, closely rivaling GPT-4's 84.2 (76.2) and further elevates to 91.6 (84.6) with synthesized human feedback from GPT-4. OpenCodeInterpreter brings the gap between open-source code generation models and proprietary systems like GPT-4 Code Interpreter. |
| title | OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement |
| topic | Software Engineering Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2402.14658 |