Prepending a Hindi filler paragraph to WMDP-bio questions restores 57.3% accuracy in ELM-unlearned models, showing the unlearning is superficial output suppression rather than true knowledge removal.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
Prepending a Hindi filler paragraph to WMDP-bio questions restores 57.3% accuracy in ELM-unlearned models, showing the unlearning is superficial output suppression rather than true knowledge removal.