通过稀疏更新低敏感参数，实现高效且无冲突的模型任务编辑。
Efficient Model Editing with Task-Localized Sparse Fine-tuning
- 仅更新预训练模型中对任务不敏感的少量参数，避免线性化计算开销。
- 在任务加法与反向操作上优于现有方法，训练与推理效率显著提升。
- 适合需要模块化调整的基础模型部署场景，如多任务系统集成。
任务算术已成为一种有前景的模型编辑方法，通过可组合的任务向量表示特定任务知识。然而，现有方法依赖网络线性化来提取任务向量，导致训练和推理时存在计算瓶颈。此外，仅靠线性化无法保证权重解耦——这是实现任务向量无冲突组合的关键特性。为此，我们提出TaLoS，可在无需显式线性化和跨任务信息共享的前提下构建稀疏任务向量。我们发现，预训练模型中存在一组参数在各类任务下梯度敏感度始终较低，仅稀疏更新这些参数即可在微调过程中促进权重解耦。实验表明，TaLoS在保持高效训练与推理的同时，在任务加法与否定任务上均优于当前方法。该方法支持模块化参数编辑，有助于推动可适配基础模型在实际应用中的落地。
原文摘要 · Abstract (English)
Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, leading to computational bottlenecks during training and inference. Moreover, linearization alone does not ensure weight disentanglement, the key property that enables conflict-free composition of task vectors. To address this, we propose TaLoS which allows to build sparse task vectors with minimal interference without requiring explicit linearization and sharing information across tasks. We find that pre-trained models contain a subset of parameters with consistently low gradient sensitivity across tasks, and that sparsely updating only these parameters allows for promoting weight disentanglement during fine-tuning. Our experiments prove that TaLoS improves training and inference efficiency while outperforming current methods in task addition and negation. By enabling modular parameter editing, our approach fosters practical deployment of adaptable foundation models in real-world applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。