- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper addresses residual factual recovery in vision-language unlearning: suppressing a target answer’s original wording may leave the same fact accessible through paraphrases, indirect questions, or visual evidence. It proposes RAMP, a two-stage method. Stage I suppresses verified target answer spans. Stage II uses teacher-forced scores of verified alternative answers to activate additional representation penalties and allocates their weights across text, image, and fusion intervention sites using gradient sensitivity. Alias suppression and several preservation objectives remain active alongside these penalties. Experiments on LLaVA-1.5-7B cover CLEAR and UMU-Bench. On CLEAR, Stage II reduces held-out paraphrase recovery from 0.181 to 0.072 and indirect recovery from 0.174 to 0.089. Equal, shuffled, and single-route controls assess adaptive weighting, while shared-supervision baselines examine the contribution of additional data. The paper also evaluates unseen attacks, output quality, public utility-data substitution, and computational cost.
Critical strengths
- The problem formulation is supported by quantitative evidence, and the evaluation goes beyond direct-answer suppression. The observed gap between direct recovery and paraphrased or indirect recovery provides a concrete motivation for residual-guided updates. Held-out questions and images, multiple attack families, and output audits test whether improvements extend beyond the training aliases and whether reduced disclosure merely reflects refusal or degenerate generation. This is consequential because direct-answer accuracy alone can substantially overstate successful unlearning. The paper also appropriately distinguishes its empirical suppression results from complete information erasure or equivalence to retraining.
- The controlled experiments provide meaningful support for target-dependent route weighting. Adaptive, equal, shuffled, and single-route variants share initialization, supervision, other losses, and Stage-II update budgets. In particular, shuffling preserves the distribution of weight vectors while breaking their association with targets, making it a useful control for the proposed adaptive mechanism. Shared-supervision baselines separately show that span and alias construction help existing methods but do not fully reproduce RAMP’s results. Together with the forgetting–preservation measurements, these experiments make the methodological contribution more convincing than a comparison against unaugmented baselines alone.
Critical weaknesses
-
The rationale and robustness of the residual-guided routing rule are not fully established. The gap between direct and semantic recovery convincingly motivates further unlearning, but does not by itself justify allocating representation penalties according to cross-route gradient magnitudes. Text, image, and fusion sensitivities are computed over different tensors using different operations, without dimension normalization, so their relative values may reflect representation scales or token counts as well as target-relevant sensitivity. Equal and shuffled controls demonstrate the usefulness of target-dependent weighting in the evaluated setting, but comparisons with normalized sensitivities or validation-tuned constant weights are needed to substantiate the particular allocation rule. Evaluation on only LLaVA-1.5-7B further limits confidence in the robustness of this architecture-dependent design.
-
The evaluation leaves target-level protection under repeated extraction attempts unclear. The paper provides substantial evidence of reduced average recovery through held-out questions, reserved images, and unseen attacks. However, its metrics average query outcomes within identities rather than measuring whether an identity can be recovered by at least one attempt. Consequently, low average recovery may coexist with a substantial proportion of compromised targets. The attack suite covers 20 identities with three prompts per family, leaving protection under larger query budgets insufficiently characterized. Although the paper appropriately avoids claiming complete erasure, identity-level compromise rates are important for assessing the practical significance of its unlearning gains.
Questions for authors
How well does the teacher-forced residual score predict actual output-based recovery, particularly for examples below the activation threshold? Do dimension-normalized sensitivities or validation-tuned constant route weights preserve RAMP’s advantage? How sensitive are the adaptive weights to question length, image-token count, and the selected inspection layers?
3 comments
Response to Reviewer RF7R (2/2): the residual score, repeated attempts, and outputs
1. Does the training score predict output leakage, especially below the threshold? We have not measured a per-example calibration curve or a below-threshold false-negative rate, and we will state this. The design limits the consequence of a miss: (i) log(0.02) is a cut on the length-normalized score, not a 2% leakage rate; (ii) below it, aliases are still suppressed at one-fifth strength and all preservation losses stay on; (iii) the score is recomputed at every later visit, so an example whose aliases regain likelihood returns to the active branch; and (iv) checkpoints are selected on recovery rates for separate paraphrased and indirect validation questions, so leakage that the score misses is penalized at selection.
What the paper shows is that updates guided by the score reduce generated-answer recovery on prompts the score never sees. The post-training attack suite uses 20 identities, three prompts per family, and reserved images, and none of its prompts was used for training or checkpoint selection (Table 19). "No route penalty" is Stage II with alias suppression but without the representation penalties:
| Attack family | Stage I ↓ | No route penalty ↓ | RAMP ↓ |
|---|---|---|---|
| Long-tail paraphrase | 0.260 | 0.137 | 0.091 |
| Visual clues | 0.268 | 0.160 | 0.098 |
| Two-hop relations | 0.286 | 0.183 | 0.111 |
| Candidate disambiguation | 0.224 | 0.131 | 0.084 |
| Two-turn dialogue | 0.310 | 0.199 | 0.124 |
The last two columns start from the same Stage-I checkpoint and suppress the same aliases; the score-weighted penalties lower recovery in every family. This supports the update that the score guides, not the calibration of the score itself.
2. Average recovery vs. identity-level compromise. You are right. Our metric averages prompts within each identity and then across identities, so it cannot determine the share of identities recovered by at least one of several attempts; a low mean is compatible with many compromised identities. Only the two-turn family applies an OR, and only within one dialogue. We will (i) describe the results as reduced average recovery under the specified tests, not as protection against repeated attempts, and (ii) report identity-level any-hit rates and query-budget curves computed from the stored attack generations.
3. Lower recovery is not refusal or fluent error. On CLEAR forget queries (Table 20), from Stage I to RAMP, refusals fall from 7.1% to 4.1%, semantic-only disclosure from 15.6% to 2.9% (CLEAR's Gold model, never trained on these identities: 3.0%), and wrong non-target facts from 13.6% to 8.6% (Gold: 8.3%). Accuracy on harmless questions about the same images rises from 88.6% to 90.3% (Gold: 89.6%).
Ethics flag. All forgotten identities are fictitious benchmark characters (CLEAR, UMU-Bench), and the attacks are used only to measure residual disclosure. We are happy to clarify further.
Thank you again for these precise questions. We hope the rationale for following the residual, the evidence that its benefit is target-specific and efficient, and the explicit metric boundaries strengthen your confidence in the contribution.
Follow-up: happy to clarify any remaining questions
Dear Reviewer RF7R,
Thank you again for your time and thoughtful feedback. With only a few hours remaining in the discussion period, we would greatly appreciate your thoughts on our responses and additional evidence. We are eager to address any remaining questions and discuss any points that are still unclear, and will respond promptly.
Best regards,
The Authors of Submission #36225
Response to Reviewer RF7R (1/2): why allocating by residual sensitivity helps
Thank you for your positive assessment and for highlighting the shuffled control and the multi-condition evaluation. We agree with your key distinction: showing that recovery must be reduced under several access conditions does not by itself justify raw cross-route gradient magnitudes as the allocation signal. Below we explain the rationale, what the existing controls establish, and where the limits are.
1. Rationale. The residual score is a soft maximum of the teacher-forced log-likelihoods of the verified alternative answers (aliases), i.e., how easily the model can still state the fact after Stage I has suppressed the direct answer. Its gradients with respect to the question embeddings, the projected image tokens, and answer-to-image attention (attention × gradient) measure how strongly this remaining likelihood depends, locally, on each part of the input. Each sensitivity weights a penalty that moves the corresponding features away from those of the original model until a similarity margin is reached: image-free question states (text), vision-encoder and projected image features (image), and answer states and attention patterns while producing the alias (fusion). The weights are detached and smoothed per example, so the optimizer changes the model under a fixed allocation rather than learning the allocation (App. C.1, C.3).
2. The penalties are distinct levers, and adaptive weights use them better. All rows share the Stage-I checkpoint, data, other losses, and 1,200 Stage-II updates (three seeds; Tables 15, 16):
Each single-route penalty is best in its own condition and weak elsewhere, so which lever a target needs matters. Adaptive weights beat equal weights in all three conditions at once, rather than trading one condition against another, and have the lowest worst-condition recovery (0.081 vs. 0.112). Relative to training without the penalties (route-loss weight λ6 = 0; question+image recovery 0.151, Table 26), equal weights remove 0.039 of question+image recovery at a cost of 0.019 in native utility (fixed examples from the original instruction-tuning distribution), whereas adaptive weights remove 0.070 at a cost of 0.006.
3. Target signal or scale artifact? (a) A fixed scale difference between routes, whether from feature dimensions, the number of layers, or the operation type, affects every target alike, so it is also present in the shuffled control, which reuses the same weight vectors for other identities. Shuffled weights are worse than equal weights on every metric (paraphrase recovery 0.113 vs. 0.094, against 0.072 for adaptive; UMU-10% UC, the remaining target performance, 0.5918 vs. 0.5712, against 0.5474). The benefit therefore comes from matching weights to their own target, not from the distribution of weights. (b) Image-token count cannot drive the image sensitivity here: LLaVA-1.5 always supplies 576 projected tokens per image. (c) Following the sensitivities more closely helps up to a point. Equal weights are the τa → ∞ limit, and question+image recovery is 0.112 there, 0.105 at τa = 4, 0.081 at the default τa = 2, and 0.090 at τa = 1 (τa = 1 and 4 use one seed; Table 26).
4. Limits. Question and alias lengths vary and enter the text and fusion sums. We have not measured how the weights correlate with them, nor tested dimension-normalized scores, validation-tuned constant weights, or other inspection layers (fixed at decoder layers {8, 16} and {20, 24, 28, 31}). Among constant allocations, we tested the simplex center (equal) and its three corners (single routes); adaptive weights are better than all four on held-out paraphrase and indirect recovery and on worst-condition recovery. We therefore present the rule as an empirically supported, locally measured heuristic for LLaVA-1.5-7B, not as a localization of stored facts, and will state these limits in the paper.