LFPM mitigates backdoors in model merging by optimizing an anti-backdoor task vector in feature space under the Cross-Task Linearity framework to suppress backdoors without major clean-task degradation.
On the emergence of cross-task linearity in the pretraining- finetuning paradigm.arXiv preprint arXiv:2402.03660,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.
citing papers explorer
-
From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging
LFPM mitigates backdoors in model merging by optimizing an anti-backdoor task vector in feature space under the Cross-Task Linearity framework to suppress backdoors without major clean-task degradation.
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.