- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This work discusses unlearning information in large-language models and relearning attacks through the lens of the internal model representations on the 'forget set'. It provides an analysis into the components of the internal representations, and characterises how existing unlearning methods are weak to relearning attacks because the majority of the update they provide to models is concentrated in the dominant components which are easy to recover. Following this intuition, they present a method which explores using minor components for unlearning as they may be more robust. Their proposed method MCU, sits on top of existing unlearning methods and enhances their defence against relearning attacks. MCU is evaluated across model families and unlearning benchmarks, and each component is ablated strongly.
Overall, this paper presents an interesting analysis of LLM internal representations under unlearning but lacks sufficient experimental validation, statistical significance, and supporting analysis to justify the approach it presents. Given the concerns presented below, if the authors were to clarify I would be very open to increasing my score.
Critical strengths
- The conceptual framework and exploration of dominant and minor components is well-structured and easy to follow, easily highlighting the need for a method which targets minor components.
- The subspace projection method which restricts the update of various unlearning methods to the minor component subspace is well-defined, well-motivated, and easy to apply to various methods. The authors have done a good job of demonstrating the general machinery, and outlining how it can be applied.
- The work presents strong ablations on subspace removal, model families, sensitivities, and component projection strategies.
Critical weaknesses
- The analysis of principal components seems to be limited to a single model and data, with ablations of unlearning methods. This is interesting, but raises questions about the model and data. Furthermore, in the Appendix results I observe some settings in which the dominant components and recovery ratio do not support the claims made by the authors.
- The main results show that MCU is complementary to existing unlearning algorithms with visible impact on forget quality as it does restrict the optimization. Because of this, and the restriction to minor components - it stands to reason that with MCU an unlearned model may be more viable to membership attacks which are a key consideration for unlearning. Can the authors expand on this?
- The authors claim that MCU substantially improves on Relearning attack defence, yet in most comparative results visible in Table 1, the improvement is marginal and experimental results are not reported over multiple seeds with mean and standard deviation - which brings into question the statistical significance of these results. Furthermore, the most notable results are achieved with a combination of CIR and MCU (with a large percentage of the share coming from CIR alone) which is not mentioned by the text.
- Additionally, the main result is that MCU + CIR gives "substantially lower post relearning accuracy and (∆) than all other configurations" yet this claim is not accurate as reflected in Table 5, (MLP Breaking + CIR + SAM outperforms), and in standalone comparisons SAM seemingly outperforms in many cases. This further calls into question what MCU is actually doing given the lack of statistically supported results.
- Targeting minor components through the loss function is intuitive and interesting, but this changes the landscape, which fundamentally changes the problem that is being achieved through optimization. What seems to now be targeted is "what unlearning can be achieved through minor component modification only" rather than "can we unlearn in a way that is robust to relearning by only modifying minor components" which is what the work claims to address. This combined with uncertainties about the experiments, makes me call into question what the proposed method is achieving.
Questions for authors
- What is the PCA of LLM representations of the presented methods with CIR, MCU? Does unlearning with CIR and/or MCU produce similar behaviour on unlearning change and/or relearning recovery? This could be a convincing result.
5 comments
W3. Independent contribution of MCU and statistical significance
Standalone contribution. The main results explicitly evaluate MCU both without CIR and on top of CIR, allowing their contributions to be distinguished. The comparisons without CIR give the following post-attack Relearn accuracies.
Paper reference: Table 1.
| Dataset | RMU → RMU + MCU | MLP Breaking → MLP Breaking + MCU |
|---|---|---|
| WMDP-Cyber | 54.6 → 53.9 | 55.8 → 52.0 |
| WMDP-Bio | 49.8 → 48.7 | 58.8 → 57.5 |
| Years | 64.3 → 54.9 | 51.5 → 49.5 |
The reported comparisons favor MCU in absolute Relearn accuracy, but several differences are small.
Additional contribution on top of CIR. The paired comparisons below hold CIR fixed. Each entry reports Relearn accuracy for base objective + CIR → base objective + CIR + MCU:
| Dataset | RMU + CIR → + MCU | MLP Breaking + CIR → + MCU |
|---|---|---|
| WMDP-Cyber | 50.5 → 43.3 | 37.2 → 31.6 |
| WMDP-Bio | 47.6 → 39.5 | 29.7 → 26.4 |
| Years | 37.4 → 33.7 | 39.4 → 30.9 |
These comparisons isolate the observed increment from adding MCU to an already effective CIR baseline. The combined result therefore includes a contribution from each method.
Why the two interventions differ. Appendix E provides a curvature-based interpretation of CIR. Under the local Fisher/GGN approximation and subspace-alignment assumptions, CIR's filtering of module inputs and output gradients retains parameter modes with lower relearning curvature. Their unlearning displacements are recovered more slowly under a limited attack budget:
\qquad \lambda_{ij}=\alpha_i\beta_j.$$ MCU instead specifies which representation directions enter the forgetting objective. These interventions operate in different spaces, connected by the model Jacobian; a filter on parameter modes does not generally impose the same objective as a transformation of representations before loss computation. This explains how both can affect recoverability while providing complementary constraints. The representation-change analysis and the paired comparisons above support this distinction empirically. The direction-wise recovery analysis and the curvature interpretation are also contributions beyond the combined method's performance. **Paper references:** Figure 3; Appendix E. **The evidence extends beyond small differences in individual cells.** The review's characterization of the gains as marginal does not account for the complete set of comparisons. The evidence supporting MCU includes: | Evidence | What it tests | Location | |---|---|---| | Standalone MCU across base objectives and datasets | Whether gains require CIR | Table 1 | | Adding MCU while keeping CIR present | The increment beyond the CIR baseline | Table 1 | | Nearly matched Forget accuracy and comparable WikiText loss | Whether gains arise from weaker initial forgetting | Table 6 | | Adaptive representation-restoration attack | Whether gains persist when the attack targets internal representations | Table 7 | | Additional model families | Whether the intervention transfers beyond the main model | Table 8 | The direction of improvement is consistent across these evaluations, and the CIR-controlled comparisons include substantial reductions in post-attack accuracy. The conclusion is supported by this repeated pattern across experimental conditions, rather than by treating a small difference in one cell as decisive. Variation in the magnitude of the gains does not explain away their consistency or the matched-Forget evidence. **Observed robustness and statistical testing are distinct claims.** The tables report empirical attack outcomes; we do not characterize them as results of a repeated-seed significance test. Cross-setting consistency is not a substitute for such a test, but it is relevant evidence for the method's effectiveness. Accordingly, the absence of seed-wise error bars does not by itself substantiate the suggestion that MCU contributes little beyond CIR or fails to improve robustness.W4. SAM comparison and the claim of superiority over all configurations
The cited SAM result does not contradict MCU's incremental contribution. The comparison in the main-results discussion concerns the configurations in the main table. The complete results additionally include SAM combinations. The relevant question is whether MCU improves the corresponding unlearning pipeline and whether the broader comparison supports that contribution.
For MLP Breaking + CIR, the full robustness–utility comparison is shown below.
Paper references: Table 1 (main comparison); Table 5 (complete results).
| Dataset | Method | MMLU ↑ | WikiText ↓ | Relearn ↓ | Δ ↓ |
|---|---|---|---|---|---|
| WMDP-Cyber | MLP Breaking + CIR | 65.0 | 1.001 | 37.2 | 17.0 |
| + SAM | 65.3 | 1.005 | 28.5 | 2.3 | |
| + MCU | 64.7 | 1.001 | 31.6 | 5.7 | |
| WMDP-Bio | MLP Breaking + CIR | 64.8 | 1.001 | 29.7 | 7.6 |
| + SAM | 64.9 | 1.002 | 31.4 | 5.5 | |
| + MCU | 64.5 | 1.001 | 26.4 | 3.6 | |
| Years | MLP Breaking + CIR | 64.6 | 1.010 | 39.4 | 6.7 |
| + SAM | 64.3 | 1.021 | 36.9 | 10.3 | |
| + MCU | 63.8 | 1.010 | 30.9 | 5.0 |
The complete comparison favors consistency over a single-task ranking. SAM achieves the lower attack accuracy on Cyber. MCU achieves lower Relearn and Δ on Bio and Years, while matching the baseline's WikiText ratio across the datasets. Moreover, MCU improves both Relearn and Δ relative to the same CIR baseline throughout; SAM raises Relearn accuracy on Bio and raises Δ on Years. The Cyber result therefore establishes a setting in which SAM is stronger, rather than showing that MCU's contribution is absent or generally inferior.
Standalone comparisons also require accounting for utility. For MLP Breaking without CIR, SAM has lower Relearn accuracy, accompanied by lower MMLU than MCU.
Paper reference: Table 5.
| Dataset | + SAM MMLU ↑ | + MCU MMLU ↑ | + SAM Relearn ↓ | + MCU Relearn ↓ |
|---|---|---|---|---|
| WMDP-Cyber | 58.0 | 60.4 | 47.4 | 52.0 |
| WMDP-Bio | 57.5 | 60.3 | 48.5 | 57.5 |
| Years | 58.0 | 61.5 | 47.4 | 49.5 |
These are different robustness–utility operating points. They do not establish that SAM dominates MCU. MCU's contribution is the spectral explanation and the associated intervention that improves the paired baselines, including at matched initial forgetting. That claim is supported even when another method wins a particular configuration.
We will make the comparison set explicit in the main-results discussion and discuss the SAM trade-offs using the complete results.
W5. Does modifying the objective change the unlearning task?
The optimization objective changes; the evaluated unlearning task does not. Designing a surrogate that favors changes resistant to recovery is precisely the proposed approach to robust unlearning. MCU is evaluated on forgetting target knowledge, retaining general utility, and limiting held-out recovery under attack—not on minimizing the projected loss alone. Changing the surrogate therefore does not turn the evaluation into a different task.
Loss signal and actual changes. MCU directs the representation-level loss toward selected directions; it does not impose a hard constraint that every resulting representation change occurs only in those directions. Parameter sharing and the model Jacobian can couple changes across directions and layers. We will distinguish the targeted loss signal from the actual changes measured in the representation-change analysis.
Paper reference: Figure 3.
Matched-Forget evidence. The following comparison helps separate attack robustness from a change in initial forgetting strength.
Paper reference: Appendix I, Table 6.
| Dataset | Method | Forget | Relearn | WikiText ratio |
|---|---|---|---|---|
| WMDP-Cyber | MLP Breaking + CIR | 23.6 | 38.9 | 1.0001 |
| + MCU | 23.9 | 32.6 | 0.9991 | |
| WMDP-Bio | MLP Breaking + CIR | 23.2 | 29.6 | 1.0007 |
| + MCU | 22.8 | 25.4 | 1.0005 |
Here, MCU achieves lower Relearn accuracy at nearly identical Forget accuracy and comparable WikiText loss. This directly addresses whether the altered objective improves robustness at comparable initial forgetting strength. These comparisons match forgetting and utility rather than training steps; MCU requires more updates at these operating points.
We thank the reviewer for the constructive assessment of our representation analysis, the subspace intervention, and the ablations. We clarify the existing evidence for MCU's contribution, its relationship to CIR, and the scope of the evaluation below.
W1. Scope of the PCA analysis and exceptions to the recovery trend
Scope of the existing analysis. The paper evaluates the observations across objectives, sample sizes, and parameterizations:
These experiments provide evidence that the observations extend beyond a single loss, fit sample size, or parameterization. Cross-model behavioral evidence is reported separately below.
How to interpret exceptions in the curves. Our mechanism concerns the relationship between the concentration of unlearning changes and their relative recoverability; it does not require recovery to decrease monotonically at every PC index or vanish in later directions. Some CIR curves show an initial decline followed by a flatter tail with substantial recovery. This qualifies the strength of the spectral separation in those settings, but does not by itself negate the greater recoverability of the leading directions. We will make this distinction explicit and avoid wording that suggests every minor component is immune to recovery.
Joint interpretation of change and recovery. The recovery ratio measures the fraction of an unlearning displacement that is reversed. It should be read alongside the change ratio: a large recovery fraction in a direction with little initial displacement has a different significance from recovery of a direction carrying much of the unlearning change. The paper reports both metrics for this reason. The theory explains the spectral tendency under its stated local approximations.
Behavioral generality across model families. Each entry below shows Relearn accuracy for MLP Breaking + CIR → MLP Breaking + CIR + MCU.
Paper reference: Appendix K, Table 8.
Adding MCU lowers Relearn accuracy across the reported settings, supporting transfer of the intervention across model families. This is behavioral evidence of generality; detailed cross-model recovery profiles are a separate mechanistic test.
W2. Forget quality and membership-inference risk
Effect on initial forgetting. The reported results do not support the premise that MCU systematically weakens forgetting. The following table compares MLP Breaking + CIR → MLP Breaking + CIR + MCU.
Paper reference: Table 1.
Initial Forget accuracy varies in both directions, while post-attack Relearn accuracy improves across these settings. On Cyber, MCU reaches approximately chance-level accuracy; the baseline's lower-than-chance accuracy alone does not establish more complete knowledge removal. The matched-Forget comparison below directly controls for different starting accuracies. We will emphasize absolute Relearn accuracy alongside the gap Δ.
Membership inference is a separate evaluation question. Restricting the representation-level objective does not, by itself, imply greater vulnerability to membership inference. Neither task accuracy nor the choice of subspace determines whether members can be distinguished from comparable nonmembers. Our current experiments evaluate knowledge recovery rather than membership inference, so we make no claim of improved membership privacy and have no evidence that MCU increases membership leakage.
Scope of the claim. A dedicated membership-inference evaluation would require member/nonmember splits with appropriate distribution and difficulty controls. We will distinguish this privacy question from the evaluated knowledge-recovery threat model. MCU's contribution here is empirical robustness against relearning, not a formal data-deletion guarantee.