论文标题
针对特定项目的代码符号化的几杆培训LLM
Few-shot training LLMs for project-specific code-summarization
论文作者
论文摘要
非常大的语言模型（LLM），例如GPT-3和Codex在几个自然语言任务上已经达到了最先进的性能，并且对代码也表现出了巨大的希望。 LLM的一个特别令人兴奋的方面是他们进行几次射击和零射门学习的诀窍：他们可以学习执行很少的示例的任务。很少有射击在软件工程中具有特殊的协同作用，那里有很多现象（标识符名称，API，术语，编码模式），这些现象被称为高度特定于项目的现象。但是，特定于项目的数据可能非常有限，尤其是在项目历史的早期；因此，LLM的几次学习能力可能非常相关。在本文中，我们研究了使用非常大的GPT（生成预训练的变压器）代码模型的少量训练，并找到证据表明，表明人们可以显着超过最新的代码符号模型，利用特定于项目的特定培训。
Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A particularly exciting aspect of LLMs is their knack for few-shot and zero-shot learning: they can learn to perform a task with very few examples. Few-shotting has particular synergies in software engineering, where there are a lot of phenomena (identifier names, APIs, terminology, coding patterns) that are known to be highly project-specific. However, project-specific data can be quite limited, especially early in the history of a project; thus the few-shot learning capacity of LLMs might be very relevant. In this paper, we investigate the use few-shot training with the very large GPT (Generative Pre-trained Transformer) Codex model, and find evidence suggesting that one can significantly surpass state-of-the-art models for code-summarization, leveraging project-specific training.
