A post-training pipeline combining SFT, GRPO reinforcement learning, and corrective self-consistency lifts 0.5B-1.5B models to 56.9%-67.1% execution accuracy on BIRD dev.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
A post-training pipeline combining SFT, GRPO reinforcement learning, and corrective self-consistency lifts 0.5B-1.5B models to 56.9%-67.1% execution accuracy on BIRD dev.