Tag
This paper introduces Prefix-Denoising Consistency (PDC), a test-time verification method for Diffusion Language Models that improves performance on reasoning tasks by using prefix-conditioned regeneration and majority voting.
本文提出GradeSQL框架,使用结果奖励模型(ORM)进行Text-to-SQL的测试时验证,在BIRD和Spider基准上分别比基于执行的Best-of-N方法提升4.33%和2.10%。