- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes SafetyTransfer, a knowledge transfer framework for safety alignment in small language models, aiming to improve their ability to distinguish between harmful and harmless requests while mitigating over-refusal. The method first extracts low-rank safety contrastive subspaces from the teacher model using SVD. It then constructs a token-semantic interface based on the LM Head to transfer safety-related representations to the student model, which is trained through response supervision and representation alignment. Experiments across multiple model families and safety evaluation datasets demonstrate that the proposed method effectively reduces over-refusal and improves selective-refusal performance.
Critical strengths
-
The paper addresses the balance between refusal capability and helpful responses in the safety alignment of small language models. The research motivation is clear, and the problem has practical relevance.
-
The proposed method extracts safety-related representations using low-rank contrastive subspaces and employs the LM Head for cross-dimensional transfer, avoiding direct alignment of complete hidden states or the need to train additional cross-dimensional projection networks. Its effectiveness is validated across three model families and multiple datasets, demonstrating consistent improvements in Gap and SR-H. Ablation studies further support the effectiveness of several key design choices.
Critical weaknesses
-
All three teacher–student model pairs evaluated in the paper belong to the same model family. Since the proposed method relies on shared token identities to establish semantic correspondence across models, its effectiveness may be affected by differences in vocabularies, tokenizers, and hidden representation structures. Therefore, its applicability to heterogeneous models remains to be explored.
-
The extracted subspaces may be influenced by the training data distribution, and the dominant deviation directions may not necessarily capture generalizable safety-discriminative information. It remains unclear whether the current results demonstrate robust cross-dataset transferability.
-
The experiments are limited to student models with 0.6B–1B parameters, without evaluation on larger student models. In addition, the existing metrics mainly focus on harmful refusal rates and over-refusal rates on harmless requests. However, a lower over-refusal rate does not necessarily indicate that the model can provide accurate and helpful responses to benign requests. The paper lacks an evaluation of the student's general task capabilities after safety transfer.
-
The proposed method requires scoring and selecting hidden layers from the teacher model. However, it remains unclear whether different datasets require different layer selections or whether a fixed set of layers can be consistently used across multiple datasets.
-
The paper constructs low-rank contrastive subspaces using SVD, where the subspace dimensionality directly determines the amount of representation information retained. However, a systematic analysis of different subspace dimensions is missing. I suggest conducting a rank sensitivity analysis to investigate how different values of (r) affect HR, OR, Gap, and SR-H.
Questions for authors
None
5 comments
Response for Reviewer H3Z9 [2/2]
[Weakness 4] Does SafetyTransfer require dataset-specific teacher-layer selection, or can fixed layers be reused across datasets?
Although teacher-layer selection is data-driven, our additional experiments show that dataset-specific reselection is not always necessary. For Qwen3-8B→Qwen3-0.6B, the top seven layers selected from PAN ({19, 20, 21, 22, 23, 24, 25}) overlap with six of the seven layers selected from WGM ({19, 20, 22, 23, 24, 25, 26}). To further test layer reusability, we fixed the PAN-selected layers and trained SafetyTransfer on WGM without reselecting teacher layers, while keeping the training configuration and number of supervised layers identical. The test results are:
| Layer selection | HR (%) ↑ | OR (%) ↓ | Gap ↑ |
|---|---|---|---|
| WGM-specific selection | 89.12 | 26.88 | 62.25 |
| Fixed PAN-selected layers | 88.46 | 24.87 | 63.59 |
The fixed-layer setting achieves comparable HR while reducing OR by 2.01 percentage points and improving Gap by 1.35 points. These results demonstrate that teacher-layer selection can be reused across datasets without sacrificing selective-refusal performance in this setting. We will incorporate this comparison into the revised manuscript to further demonstrate the flexibility of SafetyTransfer in teacher-layer selection and its ability to reuse selected layers across datasets.
[Weakness 5] The sensitivity of SafetyTransfer to the contrastive-subspace rank has not been systematically evaluated.
Thank you for highlighting the importance of subspace dimensionality. We conducted an additional rank sensitivity analysis on Qwen3-0.6B trained on WildGuardMix, evaluating four fixed SVD ranks (). These values represent the actual contrastive-subspace dimensionality, rather than the LoRA rank. We kept the teacher-layer selection, training data, optimization settings, random seed, and training duration fixed, changing only the SVD rank. All configurations were evaluated on the same full test set containing 754 harmful and 945 harmless prompts.
| Rank strategy | HR (%) ↑ | OR (%) ↓ | Gap ↑ | SR-H ↑ |
|---|---|---|---|---|
| Fixed | 88.86 | 25.19 | 63.67 | 81.23 |
| Fixed | 88.73 | 27.62 | 61.11 | 79.72 |
| Fixed | 88.99 | 27.41 | 61.58 | 79.96 |
| Fixed | 89.26 | 28.25 | 61.00 | 79.55 |
| Adaptive (80% energy, max rank 32) | 89.92 | 24.44 | 65.48 | 82.11 |
HR remains highly stable across the four fixed ranks, varying by only 0.53 percentage points despite a fourfold increase in subspace dimensionality. However, increasing the rank does not consistently improve selective-refusal performance: from to , HR increases by only 0.40 percentage points, while OR increases by 3.06 points, resulting in lower Gap and SR-H. More importantly, our default adaptive strategy, which selects the rank independently for each teacher layer using an 80% cumulative squared-singular-value energy criterion with an upper bound of 32, outperforms all four fixed-rank configurations across all four metrics. These results support the use of layer-wise adaptive rank selection: retaining more dimensions does not necessarily improve selective refusal, whereas adapting the retained dimensionality to each layer's singular-value spectrum provides a more effective representation of the contrastive information. We will incorporate this analysis into the revised manuscript.
Follow-up to Reviewer H3Z9
Thank you for your careful review and constructive comments. We would greatly appreciate a brief reply on whether our rebuttal addresses your main concerns.
We tested transfer from Llama to a Qwen3-4B student and across datasets, evaluated commonsense reasoning and instruction following, and examined the effects of reusing teacher layers and varying the subspace rank.
Thank you again for your time and consideration.
Response for Reviewer H3Z9 [1/2]
[Weakness 1] The applicability of SafetyTransfer to heterogeneous models remains unclear.
We clarify that SafetyTransfer is originally designed for teacher–student pairs with compatible vocabularies, where shared token identities establish a common semantic coordinate system through their LM heads. However, we further evaluate cross-family transfer from Llama-3.1-8B-Instruct to Qwen3-4B on WildGuardMix. To connect their different vocabularies, we construct an explicit mapping between tokens with matching token strings and verify that each mapped pair decodes to the same text. We then map the teacher’s sparse token-semantic coefficients to the corresponding student token indices and reconstruct the supervision targets using the student’s semantic dictionary. This preserves the transfer procedure while replacing the original shared-vocabulary correspondence with an explicit mapping.
[Weakness 2] Are the extracted subspaces sensitive to training-data distributions, limiting cross-dataset transferability?
To examine cross-dataset transfer, we trained Qwen3-0.6B models on WJB and evaluated them on WGM without target-domain retraining or model selection. The results are as follows:
Compared with SFT, SafetyTransfer increases HR by 0.66 percentage points while reducing OR by 2.86 points on the unseen WGM dataset. This provides direct evidence that the benefits of SafetyTransfer can extend beyond its training distribution. We will incorporate this result into the revised manuscript and provide broader cross-dataset generalization for further investigation.
[Weakness 3] The experiments are limited to small student models and lack an evaluation of general task capabilities after safety transfer.
(1) Student model scale. We clarify that the goal of SafetyTransfer is to transfer harmful–harmless discrimination from larger aligned teachers to smaller students, enabling compact models to reject harmful requests while remaining responsive to harmless ones. We initially focused on compact students (0.6B–1B parameters), for which safety alignment is particularly challenging: stronger safety tuning can improve harmful refusal but also increase over-refusal on benign inputs. To further examine scalability beyond this range, we additionally trained on the Qwen3-4B student. The results on the WGM are shown in the table in the Response for Weakness 1. This extends the empirical evaluation to a 4B student and demonstrates the feasibility of the SafetyTransfer.
(2) General task capabilities. Our main experiments focus on safety datasets and assess harmful refusal and harmless acceptance through HR and OR. To further examine how safety-transfer training affects capabilities beyond selective refusal, we conducted additional PIQA and IFEval evaluations. PIQA evaluates everyday physical commonsense reasoning on 1,838 questions, while IFEval evaluates adherence to 834 verifiable instructions across 541 prompts, including formatting and length requirements.
The table reports SafetyTransfer accuracy minus SFT accuracy in percentage points, with positive values indicating improvements. For IFEval, prompt-level accuracy requires satisfying every instruction within a prompt, whereas instruction-level accuracy evaluates each requirement separately. Both use strict scoring, which checks the original response directly against the requirements.
The results indicate little adverse impact on physical commonsense reasoning measured by PIQA, with changes ranging from −0.60 to +0.43 percentage points. IFEval results are more mixed: instruction-level accuracy decreases by less than one percentage point in three settings, while larger declines occur for Llama/WGM. These findings should be considered alongside our primary objective of safety-capability transfer. The instruction-following declines do not negate the selective-refusal improvements demonstrated in our safety evaluations, but reveal a capability trade-off accompanying this specialized training. We will include these evaluations, protocol details, and discussion of this trade-off in the revised appendix.