DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization
Read the original on arXiv Machine Learning →DOW-KE is an anchor‑free knowledge‑editing method that directly optimizes weight updates across multiple layers by backpropagating the final editing objective through the entire model. Unlike traditional locate‑then‑edit pipelines that optimize intermediate activations and then apply local weight updates—leading to a closure gap—DOW-KE ensures that what is optimized is exactly what is deployed, incorporating preservation constraints within the update parameterization. Experiments on two datasets and three models show that DOW-KE achieves the highest overall Score and neighborhood Specificity in five of six evaluated settings.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.