- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes SafeQ, a safety-aware post-training quantization method intended to preserve both general capabilities and safety alignment. It reuses OmniQuant’s learnable weight clipping and learnable equivalent transformation modules, applying an MSE reconstruction loss to ordinary text and a negative log cosine similarity loss to safety-related inputs through block-wise optimization of quantization parameters. Weight-only quantization enables weight clipping alone, whereas joint weight–activation quantization uses both modules. The paper evaluates language modeling on pretrained models and safety knowledge, general task performance, and conversational quality on three instruction-tuned models, alongside inference speed and memory usage. Under W4A16 quantization, SafeQ improves average SafetyBench accuracy over OmniQuant by approximately 1.27 and 1.76 percentage points on Llama-2 and Llama-3.1, respectively, while also improving average general task accuracy. The reported deployment experiments on Llama-2-7B-Chat show an end-to-end speedup of approximately 2.33–3.01× over FP16.
Critical strengths
- The paper provides a relatively simple implementation of safety-aware model compression by jointly constraining general capabilities and safety-related representations during calibration. It optimizes clipping and transformation parameters without retraining all model weights or requiring an additional safety detector at inference time. Incorporating the safety objective directly into quantization offers a practical approach to mitigating safety degradation during compression.
- The evaluation considers capability preservation alongside deployment efficiency and demonstrates simultaneous improvements in safety knowledge and general task performance in some W4A16 settings. On Llama-2 and Llama-3.1, SafeQ improves average SafetyBench accuracy over OmniQuant while increasing average general task accuracy by approximately 0.63 and 0.48 percentage points, respectively. The inference-time and memory measurements characterize the deployment benefits of the quantized models, while the conversational evaluation and W4A4 experiments also document performance limitations across settings.
Critical weaknesses
- The central claim of preserving safety alignment is not adequately validated against the behavioral objective stated in the paper. Safety alignment is described as the ability to refuse harmful, illegal, or privacy-violating requests, whereas the main safety experiments measure multiple-choice accuracy on SafetyBench. This metric provides indirect evidence but cannot by itself establish whether refusal behavior and unsafe generation are preserved or improved after quantization. Neither the main text nor the appendix quantitatively reports harmful completion rates, jailbreak attack success rates, or over-refusal on benign requests. Moreover, the average safety score on Llama-3.1 decreases from 77.67 in FP16 to 74.43, indicating model-dependent preservation even on the chosen proxy. The evidence therefore does not adequately substantiate the stronger claims of “higher safety guarantees” or substantially resolving the safety–utility trade-off.
- The claim of being the first safety-alignment-preserving PTQ method is insufficiently distinguished from prior work. CAQ by Wee et al. [1] incorporates an alignment-preserving objective directly into PTQ, encouraging the quantized model to approach a safely aligned reference while diverging from an unaligned pretrained model. SafeQ differs in calibration data, loss formulation, and reference-model requirements, but these differences do not establish the broad first-of-its-kind claim as currently stated. Although the paper identifies implementation features such as using a single reference model, it does not establish their advantages through corresponding effectiveness or cost analyses. The incremental contribution and practical benefits over existing safety-aware quantization approaches therefore require clearer substantiation.
- The ablations mainly examine the hyperparameter sensitivity of the complete method and do not adequately isolate the contributions of safety-related data and the cosine-based loss. The paper varies calibration sample counts, optimization epochs, and the safety coefficient, but does not report matched controls that remove the safety objective or apply MSE uniformly to the same mixed calibration data. The aggregate comparison with OmniQuant therefore leaves the effects of data coverage, loss formulation, and calibration effort unresolved. On Qwen, SafeQ exceeds OmniQuant by only 0.04 percentage points in average safety accuracy while reducing average general task accuracy. Variability across calibration samples or random initializations is also unreported, limiting the assessment of the magnitude and stability of the proposed design’s benefits.
Questions for authors
- SafetyBench provides the main evidence for the safety evaluation. Could you supplement it with generation-based evaluations on held-out harmful requests, adversarial prompts, and benign requests? In particular, do improvements in safety knowledge correspond to fewer unsafe completions, and are they accompanied by increased over-refusal?
- Please clarify SafeQ’s contribution relative to CAQ [1], particularly the implications of its single-reference formulation and calibration objectives for effectiveness and cost. Q-realign [2] also builds on OmniQuant and introduces different objectives for benign and harmful inputs during quantization, although its primary goal is to recover alignment degraded by fine-tuning. Clarifying the differences in problem setting and technical design would help establish SafeQ’s positioning.
- Could you separately evaluate the effects of safety-related calibration data and the cosine-based loss under comparable data sizes and optimization budgets, and report the stability of the main improvements across calibration samples or random initializations? Please also clarify whether the AdvBench calibration segments include responses, how they are assembled into model inputs, and which token positions contribute to the safety loss.
- Please compare the quantization-stage costs of SafeQ and existing methods, including wall-clock time, peak GPU memory, and the incremental cost of safety-related calibration. The current speed and memory experiments assess deployment after quantization and do not quantify the additional effort introduced by the safety-aware design. Measurements under comparable hardware and calibration budgets would help characterize the computational cost associated with the reported safety improvements.
We sincerely thank the reviewer for the valuable and detailed feedback. We are highly encouraged by the reviewer’s recognition of SafeQ’s simple and practical design, its lack of inference-time overhead, and our transparent reporting of results and limitations.
We provide explanations for the highlighted concerns below, which we are committed to address in the next version.
Generation-based Safety Evaluation (W1, Q1)
We chose SafetyBench because it is an established and reproducible benchmark covering 7 safety dimensions, and it allows a consistent per-dimension comparison across all baselines. Figure 1 qualitatively shows that SafeQ restores refusals that baseline-quantized models lose, and MT-Bench (Figure 3) suggests that preserving safety does not cause broad over-refusal. On Llama-3.1-8B-Instruct, all quantized models fall below FP16 in ACC_S, but SafeQ retains the highest ACC_S among them. We agree that harmful-completion rates, jailbreak attack success rates and over-refusal rates would directly validate the behavioral claim. We will include them and tone down the “higher safety guarantees” and trade-off statements in the revised manuscript.
Positioning w.r.t. CAQ and Q-realign (W2, Q2)
We will remove the “first” claim. Instead, we will position SafeQ as an early safety alignment preserving PTQ that differs from CAQ/AAQ [1] in two ways:
We could not empirically compare effectiveness and cost because CAQ’s code is not publicly available. Q-realign [2] targets a different problem setting, i.e., recovering alignment degraded by fine-tuning. SafeQ instead preserves the existing alignment of a full-precision model during quantization. We will add this discussion to the revised manuscript.
Isolating Data and Loss Contributions (W3, Q3)
OmniQuant shares SafeQ’s LWC/LET framework with an MSE loss on understanding data only, so it serves as the “no safety objective” control. Our λ_SA ablation (Figure 5(c), Table 12) further shows that the weight of the cosine-based safety loss directly affects safety accuracy. Regarding the calibration data, we use 128 randomly selected 2048-token segments from AdvBench. L_S is computed over the entire block output. We agree that matched MSE vs. cosine controls and variance across seeds and calibration samples would better quantify stability. We will include them and clarify these calibration details in the next version.
Quantization-stage Cost (Q4)
SafeQ builds on OmniQuant and keeps its block-wise optimization. The only additional cost is the forward pass and loss on the safety calibration data. All our quantization runs fit on a single 24GB RTX 4500 ADA GPU with a batch size of 1. We will report wall-clock time, peak GPU memory and the incremental cost relative to OmniQuant in the revised manuscript.