Preprint
Aug 2026
Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
This work proposes Wrapper-Based Intent-Form Augmentation (WIFA), an automatic intent-group augmentation method that pairs wrapped harmful examples with structurally matched wrapped benign counterexamples, requiring no external teacher or manual per-wrapper intent labels.
Ping Wu, Haibo Tong, Feifei Zhao et al.
· 0 citations