- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces a benchmark containing approximately 14,500 visual instances across six scientific and clinical safety domains, pairing harmful and safe textual supervision with the same visual content.
The proposed method, DynaRank-U, dynamically selects low-rank adaptation dimensions based on the relative magnitudes and directional conflicts of forgetting and retention gradients, aiming to reduce access to harmful information while preserving general capabilities.
Critical strengths
1.The paper addresses fine-grained unlearning. Harmful and safe knowledge share the same visual content, making this setting more representative of the challenges of selective unlearning than removing an entire concept.
2.The method is reasonably motivated. Selecting update locations solely by gradient magnitude may damage shared capabilities, so incorporating gradient conflicts is intuitively justified.
3.Tracking both reductions in harmful response rates and retention of reasoning performance on MMLU and MMMU-Pro appropriately addresses the tradeoff between safety and capability.
Critical weaknesses
1.The benchmark may conflate harmful knowledge with safety recognition capabilities. This is the most important concern. The harmful descriptions include unsafe states, improper procedures, and hazardous conditions, yet correctly identifying these situations is often essential for a safety system.
For example, recognizing that protective equipment is being used incorrectly constitutes hazard detection. If the model can no longer answer such questions correctly after unlearning, this does not necessarily indicate improved safety.
2.The construction process for the paired hazardous and benign samples is unclear. Where do the more than 14,000 paired images come from? Were they selected from public datasets, manually created, or synthesized using image generation models? What is the granularity of the visual differences between the benign and hazardous versions?
3.Retention of general capabilities cannot substitute for retention of safety capabilities. Preserving performance on MMLU and MMMU-Pro does not establish that the model can still identify risks, explain safe procedures, or issue appropriate warnings. Independent evaluations of hazard recognition and safety advice are needed, along with measurements of excessive refusal.
Questions for authors
See weakness
7 comments
Weakness 2: The source and construction of the paired samples are unclear
StateHazard-MM contains approximately 14,500 visual instances from existing image datasets and real images collected by us, with GPT-4o-assisted hazardous and safe text annotations. We did not generate benchmark images using text-to-image diffusion ourselves. Some upstream datasets may contain generatively constructed images; our claim therefore concerns our construction process, not a guarantee that every upstream source contains only real images.
| Domain | Principal image sources |
|---|---|
| Chemical Safety | HAZMAT-13, Chemistry Lab Dataset, PubChem chemical structures |
| Biological Safety | Biohazard Detection Dataset (Roboflow), Biomedical Waste Classification, DIBaS |
| Radiation Hazards | HAZMAT-13, urban radiation monitoring dataset |
| Medical & Clinical | HAM10000, Kvasir, Wikimedia Commons medical imagery |
| PPE | CPPE-5, Chemistry Lab Dataset |
| Laboratory Safety | Chemistry Lab Dataset, Biohazard Detection Dataset, HAZMAT-13 |
We will revise Figure 1’s “Text-to-Image Diffusion” wording, which may imply that we generated the images, to show dataset curation and collected real images separately from LLM-assisted text annotation, without overclaiming upstream provenance.
Two designs must also be distinguished. In an original annotation pair, hazardous and safe texts share the same image and object but not necessarily identical operation text; this controls visual input while varying annotation content and context, not pixel-distinct visual states. The new operation-identical visual-swap evaluation instead uses Higher-risk and Stable images from matched fine-grained categories, constructed from source labels or reliable metadata. Both groups receive identical neutral and operation prompts while only the image changes. This is a fine-grained semantic control, not pixel-level counterfactual editing; we will distinguish both designs explicitly.
Weakness 3: General-capability retention does not establish safety-capability retention
We agree. The visual-swap evaluation directly measures risk recognition, state-appropriate operation responses, and unnecessary refusal:
| Visual group | Model | Neutral recognition Acc. ↑ | Neutral refusal ↓ | Operation Safe-Response ↑ | Operation refusal |
|---|---|---|---|---|---|
| Higher-risk / more reactive | Base | 84.1 | 3.8 | 91.2 | 78.4 |
| Higher-risk / more reactive | DynaRank-U | 82.2 | 9.1 | 89.6 | 76.9 |
| Stable / lower-risk | Base | 82.5 | 2.9 | 93.0 | 6.7 |
| Stable / lower-risk | DynaRank-U | 81.0 | 3.4 | 91.7 | 8.1 |
For Higher-risk inputs, a Safe-Response recognizes risk and refuses, warns, or redirects safely; for Stable inputs, it answers the benign operation normally. After unlearning, operation refusal remains high for Higher-risk images (76.9%) and low for Stable images (8.1%), with low neutral-description refusal in both groups—supporting state-appropriate responses rather than uniform refusal.
Across all eight checkpoints, safe-task accuracy uses the same Dataset B Safe Counterpart evaluation; the mean changes from 78.9% to 77.9% (per-model decreases: 0.7–1.4 points). The full recognition / safe-counterpart / over-refusal decomposition is currently available only for Qwen3-VL-32B and is being extended to the other checkpoints.
Finally, HarmBench output inspection shows response-format sensitivity but does not establish zero safety degradation: for Qwen3-VL-32B, default ASR is 40.2% (Base) and 44.0% (DynaRank-U), becoming 40.2% and 40.8% under a brief-refusal-only instruction. DynaRank-U can over-explain why it cannot answer, which is itself a potential risk; a shared residual ancestry-inference failure also confirms remaining content-safety failures. We therefore claim substantial (but not complete) preservation of general safety capability, while acknowledging explanatory drift and residual failures.
We would also like to clarify that the original paper does not rely solely on MMLU and MMMU-Pro: it already evaluates general safety behavior, including HarmBench. The additional experiments above complement those evaluations by directly assessing the domain-specific safety capabilities most relevant to StateHazard-MM—hazard recognition, state-appropriate warnings and safe alternatives, benign-task retention, and excessive refusal—rather than using general-capability retention as a substitute for safety evaluation.
We thank the reviewer again for motivating these clarifications. Our revised claim is: suppress specified hazardous annotation targets while preserving independently evaluated hazard recognition, safe alternatives, and appropriate benign responses.
We sincerely thank the reviewer for the constructive assessment, which helped us clarify the forget target, image curation, and direct evaluation of safety retention.
Weakness 1: The benchmark may conflate harmful knowledge with safety recognition
We agree that the optimization target must be distinguished from the capabilities to be preserved. The actual Dforget is not restricted to executable procedures: Section 2.2 includes actionable but unsafe procedures, operational details, risk knowledge, and handling instructions, while Appendix G.2 also includes unsafe states, improper handling, and dangerous conditions. The forget objective suppresses the likelihood of all these annotated answer targets; defining the entire set solely as “actionable unsafe assistance” would therefore be too narrow.
Our claim is instead capability-level retention: target suppression should preserve independently evaluated hazard recognition, non-actionable risk explanations, warnings, safe alternatives, and benign responses. We do not claim that every forget annotation is semantically disjoint from recognition content. For example, a PPE forget target may describe improper use or an unsafe condition, but failing a separate question such as “Is the PPE being used incorrectly?” is not desirable unlearning. We therefore measure recognition, safe alternatives, and excessive refusal independently, and will revise wording that equates the full forget set with actionable assistance.
On Qwen3-VL-32B, we relabeled held-out targets as actionable-unsafe, hazard-recognition, and non-actionable risk knowledge. Dataset A contains textually induced hazardous-process questions; Dataset B contains normal images and benign questions with corresponding safe, non-actionable target answers. Overall ASR measures recovery across hazardous probes; Actionable ASR isolates the executable-unsafe subset. Actionable ASR and Hazard Recognition are evaluated on Dataset A, and Hazard Recognition is credited whenever risk is recognized, independently of refusal wording or operational advice. Safe Counterpart is answer accuracy on Dataset B; Over-Refusal measures inappropriate refusal on these benign requests; Collateral Damage is the fraction of forgotten samples for which the Dataset B safe task also fails. These judgments are assisted by Qwen3.5-122B-A10B.
DynaRank-U reduces Overall ASR from 58.2% to 23.1% and Actionable ASR from 43.6% to 18.3%, while Safe Counterpart remains at 78.6% (98.5% of Base). Over-Refusal rises only from 8.6% to 10.1%, versus 24.8% for NPO and 25.7% for Mask-LoRA. Thus, hazardous-target recovery and executable assistance decrease without corresponding recognition loss or blanket refusal. The Hazard Recognition increase shows no retention failure, but may reflect response format or verbosity; we do not claim that unlearning improves recognition.