SERL-SQL reweights GRPO advantages using teacher-student likelihood gaps computed under execution hindsight, improving multi-turn Text-to-SQL accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning
SERL-SQL reweights GRPO advantages using teacher-student likelihood gaps computed under execution hindsight, improving multi-turn Text-to-SQL accuracy.