Across four LLMs, pitfall recall in machine-learning code averaged under 50%, with information-leakage and model-selection errors most often missed.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education
Across four LLMs, pitfall recall in machine-learning code averaged under 50%, with information-leakage and model-selection errors most often missed.