Overflip: Repetition-Induced Label Flips in Guardrail Models
Guardrail models are classifiers deployed to screen malicious prompts and responses in LLM-based services. To meet latency constraints, many lightweight guardrails adopt compact Transformer backbones (e.g., DeBERTa) that are trained with short context windows (typically 512 tokens) and rely on bucketed relative positio...
Xu He, Chih-Hsuan Lin, Hung-Mao Chen et al.
· 0 citations