一作ACL 2026Findings· Findings of ACL
E vo E dit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Sicheng Lyu · Yu Gu · Xinyu Wang · Jerry Huang · Sitao Luan · Yufei Cui · Xiao-Wen Chang · Peng Lu
摘要
Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modifications without the computational burden of full retraining. Existing approaches are mainly based on a locate-then-e...