DolphCoder：基于多样性与多目标指令微调的回声定位代码大型语言模型
DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
AI总结：
本文提出具备自我评估能力的多样化指令模型DolphCoder，通过学习多样化指令目标并结合代码评估目标来增强代码生成能力，在HumanEval和MBPP基准上表现卓越，并证实增加推理路径多样性与提升代码评估能力均能增强代码生成效果。
摘要：
代码大型语言模型（Code LLMs）在代码相关任务中表现出色。目前已有多项指令微调方法被提出，以提升预训练Code LLMs的代码生成性能。在本文中，我们提出了一种具备自我评估能力的多样化指令模型（DolphCoder）用于代码生成。它学习多样化的指令目标，并结合代码评估目标来增强其代码生成能力。我们的模型在HumanEval和MBPP基准上取得了卓越的性能，为未来的代码指令微调工作提供了新见解。我们的核心发现是：（1）通过不同推理路径增加更多样化的回答，能提升LLMs的代码能力。（2）提升评估代码解决方案正确性的能力，也能增强其生成代码的能力。
英文摘要：
Code Large Language Models (Code LLMs) have demonstrated outstanding performance in code-related tasks. Several instruction tuning approaches have been proposed to boost the code generation performance of pre-trained Code LLMs. In this paper, we introduce a diverse instruction model (DolphCoder) with self-evaluating for code generation. It learns diverse instruction targets and combines a code evaluation objective to enhance its code generation ability. Our model achieves superior performance on the HumanEval and MBPP benchmarks, demonstrating new insights for future code instruction tuning work. Our key findings are: (1) Augmenting more diverse responses with distinct reasoning paths increases the code capability of LLMs. (2) Improving one's ability to evaluate the correctness of code solutions also enhances their ability to create it.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
