- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies how the safety impact of benign fine-tuning data changes with the model state. It measures changes in risk rankings and tests the same matched sample groups from early and later checkpoints. It then proposes SABA, which updates risk scores and allocates an exclusion budget across training rounds. The main experiments show clear safety gains over static and refresh-only filters, with similar utility on the reported metrics. The paper also studies a second corpus and model family and reports cases where its scheduling rule fails.
Critical strengths
The paper connects a useful diagnosis to a practical method. The matched-group intervention gives evidence beyond changes in scores alone. On Dolly, all 16 reported interaction estimates are positive, and 15 intervals exclude zero. Under the same filtering budget, SABA lowers ASR by 16.1 and 9.3 percentage points compared with refresh-only on the two benchmarks with Llama-Guard-3. The ablations help separate the effects of re-scoring and budget allocation. The negative results on Alpaca and the failures of the initialization check also make the limits of the method clear.
Critical weaknesses
-
Two protocol details need clarification. Section 5.1 and Table 1 state a budget of 12,000 sample-passes for every arm, but three full rounds over all 5,000 samples would give 15,000 for no filtering. The matched intervention also lacks explicit training doses and optimizer-state rules for its four cells. These gaps limit verification of these controls, although the comparisons among filtered arms remain supported.
-
Some claims need a narrower scope. Table A6 shows that the tested repairs fail, mainly for GradShield; it does not establish that initialization information is generally unrecoverable. The allocation model also needs a per-round capacity constraint or a stated range where it is inactive. Its strict-interior claim needs correction because kappa = 1 gives delta = 1. These theory corrections do not change the reported comparison among filtered methods.
Questions for authors
-
What are the actual sample-passes for the no-filter arm? Please clarify its budget and report the training dose and optimizer reset or inheritance rule for each matched-intervention cell.
-
Can you limit the initialization-repair conclusion to the tested scorers and repairs, and clarify how it relates to the informative static SQSD results?
-
Can you state the capacity conditions for the allocation result and correct the strict-interior claim at kappa = 1?
Response to Reviewer WWB8
Dear Reviewer WWB8,
Thank you for the careful review, in particular for catching the protocol details below. We are glad that you found that the paper connects a useful diagnosis to a practical method, that the matched intervention provides evidence beyond changes in scores, and that the ablations and the reported failure cases make the limits of the method clear.
W1(a) & Q1: The sample-passes of the no-filter baseline.
A1: We agree with the reviewer, and correcting it does not change the comparison among filtering methods. In the submission, the no-filter baseline trained for three full epochs (15,000 sample-passes), while every filtering method trained on 12,000. We added a volume-matched baseline that trains 0.8 of an epoch per round (12,000 sample-passes; Table 2, Table A22; CatQA / HEx-PHI, Guard):
Matching the volume changes the CatQA ASR of no filtering by at most 2 points and lowers its HEx-PHI ASR by 0.4 to 6.9 points. Against the volume-matched baseline, SABA lowers the ASR by 32 to 43 points in the main setting, and its gains over refresh-only (16.1 and 9.3 points) are unchanged.
Revision. Table 2 now reports no filtering at both 12,000 and 15,000 sample-passes, and Table 3, the abstract and the text compare with the 12,000-pass baseline. Each remaining use of the 15,000-pass baseline is labeled (Table 5, Figure 4c, Figures A3 and A4, Tables A26 and A28, judge agreement and utility tests).
W1(b) & Q1: Training dose and optimizer state in the matched intervention.
A2: The runs from E and L are identical except for the starting adapter. Both use a learning rate of 5×10−6 with a cosine schedule and 10% warm-up, 10 epochs, an effective batch size of 8, the same seed, data order and matched samples. Each cell is a fresh run, so the AdamW state is re-initialized and the warm-up restarts at both states. On Qwen3-8B with seed 0, each group holds 20 to 23 samples and is trained for 30 optimizer steps from both states.
Revision. Appendix E.4 now states this protocol.
W2(a) & Q2: Scope of the repair result and its relation to the static SQSD results.
A3: We limited the conclusion to the tested scorers and repairs. The five repairs in Table A7 fail for GradShield, and three of them (larger LoRA rank, full-parameter gradients, removing leading principal components) also fail for SCOPE and He-grad (Table A19). For SCOPE, the correlation with its θ2 ranking is 0.273 before the repairs and 0.012 to 0.276 after.
This is consistent with the static SQSD results. SQSD projects each update onto a safe and an unsafe direction, which cancels most of the common gradient component, so its initial ranking already does better than no filtering (static SQSD reaches 44.8% CatQA ASR, against 61.3% without filtering and 62.4% for static GradShield). Its A is 0.23, below 0.3, so it is not deferred. Its ranking still changes after initialization (rank correlation 0.14 with the ranking after the first round), so the second check replaces it once. A ranking can therefore change a lot during training and still do better than no filtering at the start.
Revision. Section 3.3 and Appendix H.2 now state the repair result only for the tested inner-product scorers, and Section 3.3 notes that SQSD's initial ranking already does better than no filtering.
W2(b) & Q3: Capacity constraint and the κ=1 case.
A4: We made both corrections. The allocation problem (Eq. 3) now includes 0≤kt≤N, where kt is the number of samples excluded in round t and N the pool size, and Proposition 2 gives the capped water-filling solution. Proposition 1 now requires that the final, largest round stays below N, which holds in all our runs (largest kt = 4,500, in the B=6,000 budget ablation, below N=5,000). The text now states that δ=κ−1/(1−α) lies strictly inside (1,∞) only for κ∈(0,1): permanent exclusion (κ=1) gives the even split δ=1, and κ→0 gives δ→∞.
Revision. Sections 4.1 and 4.2 (Eq. 3, Proposition 1) and Appendix C (Proposition 2) contain these corrections.
Thank you again for the careful reading. We are happy to clarify anything further.