Shortcut Guardrail mitigates token-level shortcuts in pretrained language models at deployment time via gradient-based token identification and a LoRA-trained Masked Contrastive Learning module, improving accuracy under distribution shifts while preserving in-distribution performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation
Shortcut Guardrail mitigates token-level shortcuts in pretrained language models at deployment time via gradient-based token identification and a LoRA-trained Masked Contrastive Learning module, improving accuracy under distribution shifts while preserving in-distribution performance.