待翻譯：DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.16932v1 Announce Type: new Abstract: Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer as weight updates. This pipeline optimizes an intermediate representation but deploys multi-layer weight updates whose joint effect through the true forward pass is never itself optimized: regardless of how anchors are set or propagated, each update comes from a local solve, so propagation-induced attenuation and distortion go uncorrected, leaving a closure gap between anchor targets and realized edits. We propose DOW-KE, an anchor-free method built on a single principle: what is optimized must be exactly what is deployed. DOW-KE backpropagates the final editing objective through the complete model, jointly optimizing the updates of all edited layers so cross-layer propagation and coupling enter every gradient step. The same principle dictates where preservation resides: embedding the preservation projection in the update parameterization, inside the computation graph, makes every gradient act on the deployed update; post-hoc constraints would reopen the gap, and the constrained search keeps edits clear of protected knowledge. In large-scale sequential editing on two datasets and three models, DOW-KE achieves the highest overall Score and neighborhood Specificity in five of six model-dataset settings among the evaluated baselines.
AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
--> [Submitted on 5 Aug 2026] Title:DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization View a PDF of the paper titled DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization, by Ran Chen and 4 other authors View PDF HTML (experimental) Abstract:Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer as weight updates. This pipeline optimizes an intermediate representation but deploys multi-layer weight updates whose joint effect through the true forward pass is never itself optimized: regardless of how anchors are set or propagated, each update comes from a local solve, so propagation-induced attenuation and distortion go uncorrected, leaving a closure gap between anchor targets and realized edits. We propose DOW-KE, an anchor-free method built on a single principle: what is optimized must be exactly what is deployed. DOW-KE backpropagates the final editing objective through the complete model, jointly optimizing the updates of all edited layers so cross-layer propagation and coupling enter every gradient step. The same principle dictates where preservation resides: embedding the preservation projection in the update parameterization, inside the computation graph, makes every gradient act on the deployed update; post-hoc constraints would reopen the gap, and the constrained search keeps edits clear of protected knowledge. In large-scale sequential editing on two datasets and three models, DOW-KE achieves the highest overall Score and neighborhood Specificity in five of six model-dataset settings among the evaluated baselines. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.16932 [cs.LG] (or arXiv:2608.16932v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.16932 arXiv-issued DOI via DataCite Submission history From: Qianli Zhou [view email] [v1] Wed, 5 Aug 2026 09:56:07 UTC (660 KB) Full-text links: Access Paper: View a PDF of the paper titled DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization, by Ran Chen and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)