Recently, collaborative fine-tuning large language models (LLMs) has emergedas a new paradigm for utilizing private data from different parties in a mannerthat guarantees both efficiency and privacy. Meanwhile, the practical needs of the“right to be forgotten” and the frequent demands to update outdated information,have led to a burgeoning in the techniques of knowledge editing (KE) for LLMs.However, current KE methods are all designed for a single model, and directlyadapting current KE methods to collaborative learning scenarios encounters severeperformance decreases. In this study, we propose a non-destructive collaborativeknowledge editing framework COLLABEDIT that utilizes novel model fusion strategy to preserve overall editing performance. Empirical studies on two canonicaldatasets demonstrate the effectiveness and superiority of our method comparedwith other destructive baselines.