Tag: Process Supervision
All the articles with the tag "Process Supervision".
-
Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards
REWARD-SQL introduces a framework for Text-to-SQL by decomposing queries into Chain-of-CTEs and using Process Reward Models (PRMs) with GRPO and Best-of-N sampling, achieving a state-of-the-art 68.9% execution accuracy on the BIRD dataset with a 7B model.