AI RESEARCH
Residual Skill Optimization for Text-to-SQL Ensembles
arXiv CS.CL
•
ArXi:2605.21792v1 Announce Type: new Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures.