NSRU constrains LoRA updates via null-space projection of retain subspaces to jointly optimize safe-target learning, undesired-response suppression, and retention in LLM unlearning.
Position: LLM unlearning benchmarks are weak measures of progress,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning
NSRU constrains LoRA updates via null-space projection of retain subspaces to jointly optimize safe-target learning, undesired-response suppression, and retention in LLM unlearning.