热点
"知识消除" 相关文章
FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
cs.AI updates on arXiv.org 2025-10-16T04:32:56.000000Z
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
cs.AI updates on arXiv.org 2025-10-07T04:16:36.000000Z