@inproceedings{zhao-etal-2025-fedleke,
    title = "{F}ed{LEKE}: Federated Locate-then-Edit Knowledge Editing for Multi-Client Collaboration",
    author = "Zhao, Zongkai  and
      Xu, Guozeng  and
      Li, Xiuhua  and
      Wei, Kaiwen  and
      Zhong, Jiang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.733/",
    doi = "10.18653/v1/2025.findings-acl.733",
    pages = "14247--14258",
    ISBN = "979-8-89176-256-5",
    abstract = "Locate-then-Edit Knowledge Editing (LEKE) is a key technique for updating large language models (LLMs) without full retraining. However, existing methods assume a single-user setting and become inefficient in real-world multi-client scenarios, where decentralized organizations (e.g., hospitals, financial institutions) independently update overlapping knowledge, leading to redundant mediator knowledge vector (MKV) computations and privacy concerns.To address these challenges, we introduce $\textbf{Fed}$erated $\textbf{L}$ocate-then-$\textbf{E}$dit $\textbf{K}$nowledge $\textbf{E}$diting (FedLEKE), a novel task that enables multiple clients to collaboratively perform LEKE while preserving privacy and reducing computational overhead. To achieve this, we propose FedEdit, a two-stage framework that optimizes MKV selection and reuse.In the first stage, clients locally apply LEKE and upload the computed MKVs. In the second stage, rather than relying solely on server-based MKV sharing, FedLEKE allows clients retrieve relevant MKVs based on cosine similarity, enabling knowledge re-edit and minimizing redundant computations.Experimental results on two benchmark datasets demonstrate that FedEdit retains over 96{\%} of the performance of non-federated LEKE while significantly outperforming a FedAvg-based baseline by approximately twofold. Besides, we find that MEMIT performs more consistently than PMET in the FedLEKE task with our FedEdit framework. Our code is available at https://github.com/zongkaiz/FedLEKE."
}