HotGPT: How to Make Software Documentation More Useful with a Large Language Model?
HotGPT: How to Make Software Documentation More Useful with a Large Language Model?
复制标题
DOI：
10.1145/3593856.3595910
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Yi-An Su;Chengcheng Wan;Utsav Sethi;Shan Lu;M. Musuvathi;Suman Nath
中科院分区：
文献类型：
--
作者：
Yi-An Su;Chengcheng Wan;Utsav Sethi;Shan Lu;M. Musuvathi;Suman Nath
众所周知，软件系统的自然语言组件中包含有有价值的信息，如注释和手册，这些信息可以用来提高系统的性能和可靠性。过去的研究试图通过特定于任务的机器学习模型和工具链来提取这些信息。在这里，我们通过最先进的大型语言模型（例如，GPT系列）。我们的调查涵盖了三个代表性的任务：从注释中提取锁定规则，从注释中合成异常谓词，并确定性能相关的配置，它揭示了应用大型语言模型的系统维护任务的挑战和机遇。
It is well known that valuable information is contained in the natural language components of software systems, like comments and manual, and such information can be used to improve system performance and reliability. Past research has attempted to extract such information through task-specific machine learning models and tool chains. Here, we investigate a general, one-model-fit-all solution through a state-of-the-art large language model (e.g., the GPT series). Our investigation covers three representative tasks: extracting locking rules from comments, synthesizing exception predicates from comments, and identifying performance-related configurations; it reveals challenges and opportunities in applying large language models to system maintenance tasks.