2023 · 14 citations · 11 references
ComputingComputer ScienceComputational LinguisticsNatural Language ProcessingSoftware EngineeringInformation ExtractionLanguage ModelingLanguage ModelsSoftware DocumentationSoftware MaintenanceSoftware ModelingDocumentation ExtractionDocumentation GenerationDocumentation MiningLarge Language ModelsSystem Maintenance
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.
11
Lin Tan, Ding Yuan, Gopal Krishna et al. · 2007 · 268 citations
Naman Jain, Skanda Vaidyanath, Arun Iyer et al. · Proceedings of the 44th International Conference on Software Engineering · 2022 · 134 citations
Translating code comments to procedure specifications
Arianna Blasi, Alberto Goffi, Konstantin Kuznetsov et al. · 2018 · 97 citations