SOURCE-LINKED INTELLIGENCE

Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning Robustness

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Machine unlearning aims to make a model forget specific data, yet unlearned LLMs often fail to stay unlearned: brief fine-tuning can revive removed knowledge. Existing robustness predictors rely on global weight-space displacement, but distance alone can be misleading when random or destructive updates collapse performance. We argue that relearning robustness depends on update structure: robust unlearning should affect forget-critical weights while sparing retain-critical ones. We introduce the Forget-Retain Alignment Gap (FRAG), a training-free predictor that scores an update's forget-retain

Read original source ↗ Open in workspace

recordType

paper

region

Global