- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes DQ-OPD, a selective online distillation method for quantization recovery. By comparing the directions of post-training drift and quantization drift, it selectively applies teacher correction while retaining a regularization constraint toward the quantized initialization. Experiments on two Qwen3 models show that DQ-OPD improves performance after MXFP4 W4A4 quantization.
Critical strengths
1. Practical and well-motivated problem.
The paper asks an interesting question: should all quantization-induced deviations from the full-precision teacher be corrected? The selective recovery objective is well motivated and practically relevant.
2. Consistent empirical gains.
DQ-OPD improves over the strongest reported baseline on both Qwen3 models, with gains across multiple benchmarks rather than from a single task.
Critical weaknesses
1. The comparison with G-OPD is not fully controlled.
The reward scale and tuning procedure for G-OPD are not clearly specified. This makes it hard to tell how much of the gain comes from directional masking versus reward-scale choices.
2. The HMMT decoding experiment needs a stronger control.
A random-correction baseline with the same token-replacement rate would better isolate the effect of the directional rule. The reported 0.83-point gain over BF16 is also difficult to assess without uncertainty estimates.
Questions for authors
Clarification requests
-
Could the authors clarify the settings and tuning procedure for G-OPD and DQ-OPD? A matched comparison under the same would help isolate the gain from directional masking.
-
For HMMT decoding, could the authors add a random-correction control with the same replacement rate and report uncertainty estimates? This would better test whether the directional criterion selects more useful corrections.
Future work
Testing the method across more quantization settings and model families would further strengthen its generality.
2 comments
[Future work] More quantization settings and model families
Future work: Testing the method across more quantization settings and model families would further strengthen its generality.
Thank you for this encouraging suggestion. During the rebuttal, we extended the evaluation in both directions:
Another quantization format (NVFP4). DQ-OPD improves over RTN by +8.54 / +6.25 / +1.87 points on AIME-24 / AIME-25 / GPQA, and its four-benchmark average matches the BF16 model (66.64 vs. 66.62). Under this milder format, it is also slightly better than Direct-OPD (66.64 vs. 66.20).
Another model family with SFT-only post-training (Olmo3-7B-Think-SFT). With the pretrained Olmo3-7B as and Olmo-3-7B-Think-SFT as , DQ-OPD fully recovers the BF16 teacher on the four-benchmark average (59.17 vs. 59.10). It outperforms RTN by +7.17 points and Direct-OPD by +2.94 points.
In addition, Appendix C.1 reports MXFP4 without MBS on both Qwen3 models. Detailed results are given in our responses to Reviewer 4jqd (Q1) and Reviewer 3wkZ (Q1), and we will include these experiments in the revised paper.
We hope these additional results address your concerns, and we will incorporate them into the revised version. Thank you again for your helpful suggestions.
We thank Reviewer BM7w for the thoughtful review and for finding the problem practical and well motivated. We address each comment below.
[W1 & Q1] Matched-λ comparison with G-OPD
Thank you for this question. We agree that a matched comparison is the most direct way to isolate the gain from directional masking, and we have added it during the rebuttal.
λ settings and tuning procedure. For DQ-OPD, λ is chosen from the sweep λ∈{1,1.25,2,4} in Table 5, which gives λ=1.25 on Qwen3-8B and λ=4 on Qwen3-30B-A3B. The main-table G-OPD uses default value λ=1.25. All methods follow the same checkpoint selection protocol, reporting the checkpoint with the highest mean accuracy in evaluation of every 20 steps.
Matched-λ comparison. To make the comparison fully controlled, we additionally ran G-OPD over the same λ sweep on Qwen3-8B. The four-benchmark averages (AIME-24 / AIME-25 / GPQA / MMLU-Pro) are:
We find DQ-OPD is better at every matched λ, and even its weakest setting (63.18) is above the best G-OPD setting (62.11). And the main-table G-OPD already uses its best tested λ (1.25). Among the four values, λ=1.25 turns out to be the best one for G-OPD, so Tables 1–2 compare DQ-OPD with the strongest G-OPD configuration we tested.
These results confirm gain comes from the mask rather than from λ. At λ=1, G-OPD reduces to standard OPD and DQ-OPD differs from it only through the mask, yet DQ-OPD still improves the average by +2.04 points. Moreover, G-OPD degrades as λ grows, while DQ-OPD remains stable: without the mask, a larger λ also amplifies the teacher pull-back on preference-strengthening tokens, which DQ-OPD leaves uncorrected.
On Qwen3-30B-A3B, the matched comparisons at λ=1 and 1.25 show the same ordering (+0.89 and +0.77 on the four-benchmark average). Due to our limited computational resources, we were unfortunately unable to train G-OPD with λ=2 and 4 on the 30B model within the rebuttal period. Per-benchmark results are given in our response to Reviewer 3wkZ (W2/Q2). We hope this clarifies the role of λ in our comparison.
[W2 & Q2] Random-correction control and uncertainty for HMMT decoding
We thank the reviewer for this excellent suggestion. For the HMMT decoding experiment, we added a random-correction control with a matched replacement rate and report std across difference trials.
On HMMT Nov. 2025 (30 problems × 4 repeats) with Qwen3-8B W4A4, direction-guided decoding replaces the W4A4 token with the BF16 teacher token at 4.76% of the decoding steps. The random control replaces tokens with the teacher token uniformly at random at almost the same rate (4.41%). Following the paper, accuracy is computed over all 120 (problem, repeat) samplings and reported as mean ± std over the 4 repeats:
Randomly injecting teacher tokens recovers only about 45% of the W4A4-to-BF16 gap (43.33 → 47.50). At the same replacement rate, direction-guided selection closes the full gap and outperforms random replacement by +5.83 points. This suggests that the directional criterion selects more useful corrections, further benefiting from injected teacher tokens. It is also consistent with the training-time ablation in Figure 5a, where correcting a random subset of tokens at the same rate performs clearly worse than correcting preference-weakening deviations. We will add the new controlled result to the revised paper.