RepSelect isolates forget-set-specific representations via gradient PCA collapse to achieve 4-50x better post-relearning robustness than baselines across multiple models and forget categories.
Manning, Dan Jurafsky, and Chelsea Finn
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
-
RepSelect: Robust LLM Unlearning via Representation Selectivity
RepSelect isolates forget-set-specific representations via gradient PCA collapse to achieve 4-50x better post-relearning robustness than baselines across multiple models and forget categories.