A Preliminary Evaluation of Large Language Models for Data Science Code Generation

Farshad Ghorbanishovaneh, Lars Kotthoff

Published: 29 Aug 2025, Last Modified: 29 Aug 2025AutoML 2025 Non-Archival Content TrackEveryoneRevisionsBibTeXCC BY 4.0
Submission Type: Short paper
Tldr: We evaluate how well large language models can autonomously generate complete, executable machine learning pipelines for a real-world classification task.
Submission Number: 10