Unlearning one backdoor in LLMs generalizes to suppress other backdoors across three model families, with a new metric to measure activation shifts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
Unlearning one backdoor in LLMs generalizes to suppress other backdoors across three model families, with a new metric to measure activation shifts.