Shift Left with Generative AI: Automating Library Replacement
• Poster
Dr. Ipek Ozkaya presented this poster at Research Review 2024.
Publisher
Software Engineering Institute
Topic or Tag
Abstract
The Software Engineering Institute (SEI) is working to create a workflow and a prompting algorithm for a human-in-the-loop strategy that decomposes common changes in library replacement problems into smaller problems that can be more easily solved using large language models (LLMs), a form of generative AI trained on large amounts of text. This approach enables organizations like the DoD to address an open source library upgrade once and efficiently roll out automated changes to many projects.
Part of a Collection
CMU SEI Research Review 2024 Posters