- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper presents a safety monitoring method for diffusion LLMs. In particular, the proposed method uses a lightweight linear probe to classify whether a given prompt is safe or unsafe based on intermediate hidden representations obtained during the denoising process. The authors observe that the probe may repeatedly produce predictions that are close to its decision boundary, which they refer to as a “safety hesitation”. Based on the number of such hesitation steps (denoising steps where the probe is close to the decision boundary) the method decides whether to use a more expressive probe, that is trained on hesitation examples. This framework allows computational resources to be allocated to more difficult inputs. The proposed method is evaluated on three safety datasets and four diffusion LLMs, outperforming the considered probe- based baselines.
Critical strengths
- The proposed method is conceptually simple and does not require any modifications to the underlying diffusion LLM.
- Despite its relatively simple design, the method outperforms more complex probe-based baselines, such as temporal attention and LSTM probes.
Critical weaknesses
- The paper motivates a multi-step routing, but it never compares it against routing on a single uncertainty score from the first-stage probe, as in existing cascades that the authors cite (McKenzie et al., 2025; Cunningham et al., 2026). Since the authors present this multi-step routing as a key difference from prior cascades (Sec. 2, Sec. 4.1), such a comparison would have been helpful to understand the benefit of the proposed multi-step signal over the prior work.
- All four models come from the LLaDA lineage. Since the paper’s claims concern D-LLMs in general, and the hesitation signal depends on the model’s denoising dynamics, it is unclear whether the findings carry over to other D-LLMs (e.g., Dream-7B).
Questions for authors
See weaknesses.
6 comments
Summary of Revisions
The revised manuscript includes the following additions in response to your feedback:
- Added the routing-rule comparison to Appendix D.5 (Table 8), with a summary in Section 5.3.
- Added the evaluation on Dream-v0-Instruct-7B to Appendix D.7 (Table 10), and introduced this additional evaluation in Section 5.1.
Response to authors' rebuttal
[W1] Thank you for the routing-rule comparison. The numbers look good to me, and your method seems to outperform final-step routing. Would it be feasible within the discussion period to run the same comparison on WildGuardMix? This should only require test-time evaluation, right? Also, since average-margin routing performs within seed variation of -Monitor on ToxicChat, it would be interesting to see whether the two separate on WildGuardMix.
[W2] Thank you for adding the Dream results. The numbers address my concern about generalization beyond the LLaDA family.
Response to Reviewer FkfW
We are grateful for the reviewer’s careful assessment and suggestions for additional comparisons. We also appreciate the recognition of our method’s simplicity and its ability to monitor D-LLMs without modifying the underlying model.
W1: Multi-step hesitation versus simpler uncertainty-based routing
A1: Thank you for suggesting this comparison. To address your concern, we compare D²-Monitor's routing rule, the number of hesitation steps (multi-step, ours), against the final-step margin (single-step), an adaptation of the routing rule used in existing cascades to D-LLMs. Following Reviewer dEuR's suggestion, we also include two multi-step alternatives that route on the minimum or average margin across denoising steps.
We conduct this comparison on ToxicChat using LLaDA-8B-Instruct, keeping the trained probes and margin threshold τ fixed. Let ∣ds∣ denote the absolute decision margin at denoising step s, with s=1 denoting the final step. The alternatives route an example to the second-stage probe when:
D²-Monitor instead routes when nτ>λ, where nτ=∑s=1S1[∣ds∣<τ], retaining its original operating point. The results are shown below (F1: mean ± SD over seeds 0, 1, 2).
D²-Monitor improves mean F1 over final-step routing by 1.1 (MLP) and 1.3 (TimeAttn) percentage points while using fewer expected parameters. This indicates that multiple denoising steps contribute meaningfully. D²-Monitor also outperforms the other multi-step rules, minimum-margin and average-margin routing. We have added this comparison to Appendix D.5 (Table 8), with a summary in Section 5.3.
W2: Generalization beyond the LLaDA family
A2: We appreciate the suggestion to evaluate generalization beyond the LLaDA family. We additionally evaluate D²-Monitor on Dream-v0-Instruct-7B [1] using ToxicChat, following the same experimental protocol as for the other models (Appendix C).
The table below reports accuracy and F1 as mean ± SD over seeds 0, 1, 2. Best results are in bold, and second-best are underlined.
On Dream, both D²-Monitor variants outperform the strongest baseline (TimeAttn) by 1.8 F1 points with 3.8–5.1× fewer expected parameters, which shows that our approach generalizes beyond the LLaDA family. We have added the Dream results to Appendix D.7 (Table 10) and introduced this additional evaluation in Section 5.1.
[1] Jiacheng Ye et al. Dream 7B: Diffusion Large Language Models. arXiv:2508.15487, 2025.