A new dataset of 48,398 real Jupyter notebook editing events from GitHub shows that LLMs predict code edits poorly, with improved but still limited performance after fine-tuning.
Refactoring operations grounded in manual code changes,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Suggesting Code Edits in Interactive Machine Learning Notebooks Using Large Language Models
A new dataset of 48,398 real Jupyter notebook editing events from GitHub shows that LLMs predict code edits poorly, with improved but still limited performance after fine-tuning.