RASL retrieves relevant tables and columns for text-to-SQL by decomposing schemas into semantic entities, calibrating entity-type importance on training data, and using an LLM to rank candidates, beating baselines on Spider, BIRD, and Fiben.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL
RASL retrieves relevant tables and columns for text-to-SQL by decomposing schemas into semantic entities, calibrating entity-type importance on training data, and using an LLM to rank candidates, beating baselines on Spider, BIRD, and Fiben.