- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3(+1)
- Soundness
- 2
Read review
Paper summary
The paper asks whether post-hoc unlearning updates for LLMs move in the direction that retraining would take. Several main findings: 1. A selective path exists. The straight line from M0 to the retrained model is highly selective. 2. Gradient-based unlearning updates are nearly orthogonal to it. Task-vector negation is better aligned, yet no more selective. 3. The paper separates steepness (forget gain per unit of weight movement) from selectivity (forget gain per unit of retain damage): Euclidean ascent maximizes steepness; A local quadratic model prescribes preconditioning by the retain curvature; Ascent preconditioned by a diagonal retain Fisher cuts retain damage by about 10×, yet moves further from the oracle direction. 4. The direction does not transfer. Despite that the paper does not propose a remedy or a better unlearning algorithm, I personally think this paper has a meaningful perspective to better characterize the difficulty of unlearning.
Critical strengths
- Well-controlled design. A mirror forget set, a norm-matched reseed null and a calibrated “cosine ladder” make small weight-space angles interpretable.
Critical weaknesses
-
Two retrain seeds share only 0.38 of it, and it transfers across checkpoints at only 0.029. The orthogonality may therefore reflect the reference rather than a failure of the methods? Alignment with the component specific to the forget set is never measured.
-
“Matched forgetting” is far from retraining. The methods are compared at forget NLL 0.26, against the oracle’s 3.08, after only 18–120 steps. At that point they still reproduce most answers (ROUGE-L ≈ 0.78, against 0.34 for the oracle).
-
Limited scope and partial novelty. The evidence comes from one synthetic benchmark and models of at most 1.5B parameters trained to memorization. On the only real-text run, the proposed mechanism disappears while orthogonality persists. Many controls are single runs. Moreover, preconditioning by the retain curvature is the classical Fisher/Newton argument, and SOUL has already shown it for LLM unlearning.
-
Overclaims. No relearning, extraction or membership-inference test supports the implication that orthogonal updates leave the data behind. The preregistration cannot be verified.
Questions for authors
Please refer to Weaknesses. Besides: 1. How do the updates align with the forget-set-specific part of the retrain displacement, for example averaged over several retrain seeds? 2. Do alignment and selectivity change when the methods are run to oracle-level forgetting? 3. At the same forget level, do orthogonal updates leave more recoverable information than the oracle path (relearning, extraction, membership inference)? 4. What explains orthogonality on wikitext, where the steepness gap is absent?
Thank you again for your review. I wanted to follow up on my November 10 response and the additional experiments. If any of your concerns remain open, I’d be happy to clarify the results or address any questions during the discussion period.