"On the Generalization of SFT: A Reinforcement Learning Perspective with ..."

Yongliang Wu et al. (2025)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2508.05629

access: open

type: Informal or Other Publication

metadata version: 2025-09-13

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2508-05629
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2508-05629
Yongliang Wu, Yizhou Zhou, Zhou Ziheng, Yingzhe Peng, Xinyu Ye, Xinting Hu, Wenbo Zhu, Lu Qi, Ming-Hsuan Yang, Xu Yang:
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification. CoRR abs/2508.05629 (2025)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.