Valency Hub
alphaFeedback

WorksComputer Science

Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Distillation?

Qingyuan Zheng, Zhihao Dou

Published Fresh — added to the Hub within the last 30 daysv1

Publication details
License
arXiv nonexclusive license
Views
8
Status
Published
AI contributions
  • Generative AI tools
View details
Machine checks

No machine checks are available from the Hub API for this paper.