VGID constructs an intervention-induced teacher distribution via visual perturbation plus textual in-context unlearning and distills it into the student MLLM to achieve parameter-level forgetting.
arXiv preprint arXiv:2505.13312 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Distinguishable Deletion unifies knowledge erasure and refusal for LLM unlearning via an energy index that enforces boundaries during training and enables refusal at inference.
NCO enables efficient online pattern matching for negative hard and regex constraints in LLM decoding to prevent forbidden content without state explosion.
Downgrading optimizers to lower-information variants during LLM unlearning yields more robust forgetting on MUSE and WMDP benchmarks by converging to harder-to-perturb loss basins.
citing papers explorer
-
Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
VGID constructs an intervention-induced teacher distribution via visual perturbation plus textual in-context unlearning and distills it into the student MLLM to achieve parameter-level forgetting.
-
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
Distinguishable Deletion unifies knowledge erasure and refusal for LLM unlearning via an energy index that enforces boundaries during training and enables refusal at inference.
-
NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding
NCO enables efficient online pattern matching for negative hard and regex constraints in LLM decoding to prevent forbidden content without state explosion.
-
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
Downgrading optimizers to lower-information variants during LLM unlearning yields more robust forgetting on MUSE and WMDP benchmarks by converging to harder-to-perturb loss basins.