2 papers
cs.SE2026
Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures
Nicolas Lacroix, Frederic Precioso, Mireille Blay-Fornarino +1
Context: Once defined a taxonomy of stages structuring Machine Learning (ML) pipelines (e.g. Data Preprocessing, Modeling...), extracting these stages from source code is key for b…
cs.SE2026
Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures
Nicolas Lacroix, Mireille Blay-Fornarino, Sébastien Mosser +1
Background: Extracting the stages that structure Machine Learning (ML) pipelines from source code is key for gaining a deeper understanding of data science practices. However, the…