LLM reasoning / chain-of-thought

DIN-SQL

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

Superseded baseline#251 of 772 most-superseded · first seen Apr 21, 2023

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

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