Skip to main content
Search

Ryunyi Lee

1 related articles

Subscribe to updates
  1. arXiv

    Range-GRPO compares conformally calibrated reward intervals pairwise, achieving the highest in-distribution and out-of-distribution average performance among evaluated semi-supervised methods with fewer training resources

    The work proposes Range-GRPO, a semi-supervised post-training framework that represents LLM-as-a-Judge pseudo-rewards as conformally calibrated reward ranges and compares reward ranges pairwise within GRPO rather than reducing them to point rewards, letting interval uncertainty affect both the magnitude and direction of learning signals; theoretical analysis shows the objective recovers the GRPO advantage when all reward ranges collapse to points, and empirically Range-GRPO achieves the highest in-distribution and out-of-distribution average performance among the evaluated semi-supervised methods while requiring fewer training resources.

You’re all caught up