让开源代码模型学会调用辅助函数，性能超越GPT-4o
Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation
- 通过查询注入或响应前缀引导模型调用辅助函数
- 开源模型在代码生成任务上超越GPT-4o
- 适合希望提升代码生成效率的开发者
我们研究了基于代码预训练语言模型构建的指令微调模型在可访问辅助函数时的代码生成行为。通过将辅助函数添加到查询中或提供响应前缀，设计了几种方法来引导模型利用辅助函数，并结合指令遵循能力。实验结果表明，将基础模型的辅助函数使用能力与指令遵循能力结合具有显著效果。特别地，采用本方法的开源语言模型在性能上超越了近期强大的专有模型GPT-4o。
原文摘要 · Abstract (English)
We study the code generation behavior of instruction-tuned models built on top of code pre-trained language models when they could access an auxiliary function to implement a function. We design several ways to provide auxiliary functions to the models by adding them to the query or providing a response prefix to incorporate the ability to utilize auxiliary functions with the instruction-following capability. Our experimental results show the effectiveness of combining the base models' auxiliary function utilization ability with the instruction following ability. In particular, the performance of adopting our approaches with the open-sourced language models surpasses that of the recent powerful proprietary language models, i.e., gpt-4o.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。