The fine-tuning of Large Language Models (LLMs) specialized in code
generation has seen notable advancements through the use of open-domain coding
queries. Despite the successes, existing methodologies like
\textit{Evol-Instruct} encounter performance limitations, impeding further
enhancements in code generation tasks. This paper examines the constraints of
existing prompt evolution techniques and introduces a novel approach,
\textit{Instruction Fusion} (IF). IF innovatively combines two distinct prompts
through a hybridization process, thereby enhancing the evolution of training
prompts for code LLMs. Our experimental results reveal that the proposed novel
method effectively addresses the shortcomings of prior methods, significantly
improving the performance of Code LLMs across five code generation benchmarks,
namely HumanEval, HumanEval+, MBPP, MBPP+ and MultiPL-E, which underscore the
effectiveness of \textit{Instruction Fusion} in advancing the capabilities of
LLMs in code generation.

本文研究现有的代码生成方法的性能限制，并引入了一种新的方法 Instruction Fusion（IF），该方法通过混合两个不同的提示来增强代码 LLM 的训练提示的演化，实验结果显示该方法显著改善了代码 LLM 在五个代码生成基准测试中的性能。

指令融合：通过混合方法推进提示演进

Instruction Fusion: Advancing Prompt Evolution through Hybridization

Training large language models (LLM) with open-domain instruction following
data brings colossal success. However, manually creating such instruction data
is very time-consuming and labor-intensive. Moreover, humans may struggle to
produce high-complexity instructions. In this paper, we show an avenue for
creating large amounts of instruction data with varying levels of complexity
using LLM instead of humans. Starting with an initial set of instructions, we
use our proposed Evol-Instruct to rewrite them step by step into more complex
instructions. Then, we mix all generated instruction data to fine-tune LLaMA.
We call the resulting model WizardLM. Human evaluations on a
complexity-balanced test bed show that instructions from Evol-Instruct are
superior to human-created ones. By analyzing the human evaluation results of
the high complexity part, we demonstrate that outputs from our WizardLM model
are preferred to outputs from OpenAI ChatGPT. Even though WizardLM still lags
behind ChatGPT in some aspects, our findings suggest that fine-tuning with
AI-evolved instructions is a promising direction for enhancing large language
models. Our codes and generated data are public at
this https URL

本文介绍了一种使用大型语言模型（LLM）替代人类创建指令数据的方法，通过使用我们提出的 Evol-Instruct，从一个初始指令集开始，逐步将其重写为更复杂的指令，然后将生成的所有指令数据混合起来，以调整 LLaMA 模型，获得我们所称的 WizardLM 模型。人类评估证明，Evol-Instruct 出产的指令优于人工创建的指令，尤其是在高复杂度方面，WizardLM 模型的输出被认为比 OpenAI ChatGPT 的输出更好。尽管 WizardLM 在某些方面仍落后于 ChatGPT，但我们的研究表明，用人工智能生成的指令进行微调是提升大型语言模型的一个有前途的方向。