CAPER derives clause-aligned supervision via SQL AST counterfactuals to train a Clause-PRM that improves execution accuracy up to 15.3% relative and failure localization to 84.53% accuracy on BIRD and Spider.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ZAS-SQL distills rules from zero-shot Text-to-SQL failures to reach 87.2-88.6% execution accuracy on Spider, new zero-shot SOTA surpassing some GPT-4 few-shot and fine-tuned baselines.
citing papers explorer
-
CAPER: Clause-Aligned Process Supervision for Text-to-SQL
CAPER derives clause-aligned supervision via SQL AST counterfactuals to train a Clause-PRM that improves execution accuracy up to 15.3% relative and failure localization to 84.53% accuracy on BIRD and Spider.