A framework that uses LLM suggestions, retrieved past experience, and adaptive triggering to speed up RL search for data preprocessing pipelines, showing improved accuracy on 18 tabular datasets.
Democratizing data science through interactive curation of ml pipelines
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.DB 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
LLaPipe: LLM-Guided Reinforcement Learning for Automated Data Preparation Pipeline Construction
A framework that uses LLM suggestions, retrieved past experience, and adaptive triggering to speed up RL search for data preprocessing pipelines, showing improved accuracy on 18 tabular datasets.