-
SParC and CoSQL
The dataset used in the paper is SParC and CoSQL, two large complex cross-domain context-dependent text-to-SQL datasets. -
SMCalFlow-CS: A dataset for compositional generalization in text-to-LISP expr...
A dataset for compositional generalization in text-to-LISP expression parsing -
Spider-CG: A dataset for compositional generalization in text-to-SQL
A dataset for compositional generalization in text-to-SQL -
Improving Generalization in Language Model-Based Text-to-SQL
Two simple semantic boundary-based techniques to improve the generalization of language model-based text-to-SQL -
Text-to-sql empowered by large language models: A benchmark evaluation
DAIL-SQL is a method for text-to-SQL that uses masked question similarity selection. -
CRUSH4SQL: Collective retrieval using schema hallucination for Text2SQL
CRUSH is a method for text-to-SQL that retrieves relevant tables using the LLM hallucination.
