Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings 事件

Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings arXiv:2606.03695v1 Announce Type: new Abstract: As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for safety and compliance. Prominent methods seek persistent removal by updating the model's parameters, yet the target knowledge often can be recovered through adversarial prompting or relearning. In this work, we hypothe