SAGE is a source-agnostic post-hoc correction for LLM unlearning updates that suppresses components aligned with high-energy retained activation directions while preserving the forgetting carrier.
Ce-u: Cross entropy unlearning.arXiv preprint arXiv:2503.01224, 2025
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
-
SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector
SAGE is a source-agnostic post-hoc correction for LLM unlearning updates that suppresses components aligned with high-energy retained activation directions while preserving the forgetting carrier.