OpenCodeInterpreter: Integrating Code Generation with Execution and
  Refinement

Tianyu Zheng; Ge Zhang; Tianhao Shen; Xueling Liu; Bill Yuchen Lin; Jie Fu; Wenhu Chen; Xiang Yue

返回文献探索

Paper · arXiv 2402.14658

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

Tianyu Zheng, Ge Zhang, Tianhao Shen, Xueling Liu, Bill Yuchen Lin, Jie Fu, Wenhu Chen, Xiang Yue

84 upvotesFebruary 22, 2024arXiv 预印本

AI 摘要

OpenCodeInterpreter, an open-source system for generating, executing, and refining code, achieves high performance on benchmarks through execution and human feedback, reducing the gap with proprietary systems like GPT-4 Code Interpreter.

large language modelscode generationexecution capabilitiesiterative refinementcode systemsCode-Feedbackdatasetdynamic code refinementHumanEvalMBPPEvalPlusbenchmark evaluationaccuracy

Abstract

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.