Do Large Language Models Contain Software Architectural Knowledge? An Exploratory Case Study with GPT
Abstract
Our paper [SK25], published at the 22nd IEEE International Conference on Software Architecture (ICSA), investigates how large language models, specifically GPT-3.5, can support software engineers in discovering and reasoning about Architectural Knowledge (AK) in real-world systems such as HDFS, by assessing the accuracy, quality, and trustworthiness of GPT’s responses to architecture-related questions.
Fields of Study & Subjects
Software Engineering Research
Advanced Software Engineering Methodologies
Model-Driven Software Engineering Techniques
Publication details
- Journal / source
- Gesellschaft für Informatik (GI)
- Publication date
- 1 January 2026
- Language
- EN