Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs (opens in new tab)

Knowledge editing aims to efficiently update factual information in Large Language Models (LLMs) without full retraining. However, existing methods still suffer from performance degradation in batch knowledge editing. We identify that semantic representation entanglement, such as overlapping concepts and shared syntactic patterns, accumulates interference in the representation space and reduces editing precision. To bridge this gap, in this pa...