Unlearning aims to make a large language model behave like one retrained without its forget set. Prevailing likelihood-suppression objectives, however, lack an explicit forgetting target: they continually reward lower forget-set likelihood, making forgetting sensitive to the optimization budget. We address this limitation by estimating the direction toward the oracle without training it. Our key idea is to shrink the fine-tuned model toward its pre-fine-tuning weights and briefly re-learn the retain set, thereby removing the forget-specific contribution; in the linearized regime, this shrink-and-heal lookahead moves the model a fixed fraction of the way to the retrained model, its unique fixed point. Our method, SHIFT, extrapolates the lookahead's per-token changes into distillation targets and iteratively refines them. Evaluated against eleven baselines under a unified OpenUnlearning protocol, SHIFT achieves the highest aggregate score across all TOFU settings and the closest oracle alignment, 3.7x closer on average than the next-best method; on MUSE, it preserves the most retain knowledge. Under larger optimization budgets, baselines overshoot the oracle, while SHIFT remains near it, even under relearning attacks.
Figures & tables
Figure 1: (a) Privacy leakage on TOFU forget05 (Llama-3.2-1B) across learning rates under a fixed 10-epoch budget ( 0 : oracle; positive: the forget set looks less familiar than never-seen data). Likelihood-suppression methods overshoot the oracle, whereas Shift stabilizes near it. (b) In the linearized regime (Prop. 1 ), shrinking θ0 toward the base θb and healing on the retain set removes a fraction ρ of the forget-specific contribution; Shift extrapolates and iterates this step, which stops at the oracle θr , whereas likelihood suppression has no reason to stop there.
Figure 2: One round of Shift . (1) Shrink toward the pre-fine-tuning weights and re-fit the retain set. (2) On forget answers, the lookahead lowers the memorized token and raises the alternatives the retain set supports. (3) Extrapolating by s/ρ gives the teacher, the oracle’s next-token distribution in the linearized regime. (4) Distill it on forget tokens, anchored to θ0 on retain data; the next round looks ahead from the new model.
Figure 3: What happens when training continues, on TOFU forget05 (Llama-3.2-1B, learning rate 2⋅10−5 ): the baselines train for 20 epochs (warm-up, then linear decay over the 20 epochs) and Shift for 8 rounds. The dashed line marks the end of a standard 10-epoch run (step 60); Shift ’s standard 4 rounds end at step 48. Top: distance to the oracle (log scale); bottom: privacy leakage (0 is the oracle, positive is over-forgetting). Shift : mean over three seeds, shaded from minimum to maximum; baselines: one run, evaluated every second epoch.
Figure 4: Relearning attacks of increasing strength on Llama-3.2-1B forget05 : distance to the equally attacked oracle (mean of three attack seeds). Shift is the closest at every strength (results for all baselines refer to Appendix Table 11 ).
Machine unlearning removes the influence of selected data or concepts from trained models while preserving useful behavior and avoiding full retraining.