Method Drift›LLM reasoning / chain-of-thought
Superseded baseline#251 of 772 most-superseded
DIN-SQL
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-CorrectionLLM reasoning / chain-of-thought · first seen Apr 21, 2023
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites DIN-SQL as a baseline.
“However, pourreza2024din also noted that DIN-SQL encounters difficulties when dealing with complex queries.”
— STaR-SQL: Self-Taught Reasoner for Text-to-SQL