LLM reasoning / chain-of-thought
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here
1 papers critique it · 0 beat it on benchmarks
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.