- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The submission proposes a distillation-based framework for MLLM unlearning, leveraging a combination of visual perturbations and textual guidance. Specifically, the framework applies multimodal in-context unlearning to a teacher MLLM to construct an unlearned response distribution, which is subsequently distilled into a student MLLM via post-training. The proposed method is evaluated on three representative open-source MLLMs, demonstrating improved unlearning effectiveness compared to baseline methods.
Critical strengths
- The extension of in-context unlearning to MLLMs is beneficial, which addresses a bottleneck in MLLM unlearning.
- The overall design of the proposed framework is well-structured and easy to follow, supported by helpful illustrations.
Critical weaknesses
-
Unclear novelty. The core contribution of the submission appears to rely on extending existing in-context unlearning techniques through pre-defined visual perturbations and textual guidance. Rather than introducing a fundamental unlearning paradigm, the methodology reads primarily as an incremental extension. Given that the authors explicitly acknowledge inspiration from Zhong et al. (2026), the technical originality and standalone novelty seem limited. Besides, the application of visual perturbations in multimodal unlearning is not entirely novel. Prior work, such as AUVIC [1], has already demonstrated the effectiveness of adversarial visual perturbations (generated via a learned CLIP model) for precise MLLM unlearning. The authors should explicitly differentiate their perturbation mechanism from existing learning-based perturbation approaches.
-
Insufficient rationale and generalization analysis. In the submission, visual perturbations are primarily used to construct target response distributions for subsequent distillation. However, simpler and more direct strategies exist, such as using static refusal templates (e.g., Sorry, I cannot answer this), applying stricter prompt constraints, or completely omitting visual inputs. The authors should justify why visual perturbations are necessary or superior to these straightforward baselines. Besides, as in-context unlearning inherently supports black-box models, a compelling use case would be leveraging advanced frontier models as teachers to generate high-quality unlearned target distributions. The authors should investigate or discuss whether target distributions generated by a teacher model can successfully generalize to fine-tune student models with different architectures.
-
Incomplete experimental validation. Effective MLLM unlearning should erase the privacy information of target identity while keeping general perception intact. Following the evaluation protocol in MMUnlearner, I recommend the authors evaluate general visual perception performance on the forget set to demonstrate the robustness of the proposed unlearning framework. Besides, the experiments on model utility and copyright unlearning (Table 13 and 14) are conducted only on part of the baseline methods (i.e., GD, PO, NPO), while other baseline methods (e.g., RMU, MANU, MMUnlearner) are omitted without explanation. The authors should either provide complete comparative results across all baselines or explicitly justify their exclusion.
[1] AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
Questions for authors
- How does the pre-defined visual perturbation mechanism fundamentally differ from existing perturbation-based unlearning methods?
- Can the target unlearned distributions generated by the teacher MLLM effectively generalize to fine-tune student models with different architectures?