paper-with-me

홈 › Papers

FLEKE: Federated Locate-then-Edit Knowledge Editing

2025-02-21 · Zongkai Zhao, Guozeng Xu, Xiuhua Li, Kaiwen Wei, Jiang Zhong

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 Federated Locate-then-Edit Knowledge Editing (FLEKE), 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, FLEKE 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 FLEKE task with our FedEdit framework. Our code is available at https://github.com/zongkaiz/FLEKE.

📄 PDF Abstract BibTeX arXiv:2502.15677

Code (1)

zongkaiz/fleke 공식 구현 pytorch

Tasks

knowledge editing

Similar Papers 제목 키워드 기반

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

2024-10-08 · Zhuoran Zhang, Yongxiang Li, Zijian Kan, Keyuan Cheng 외

The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recall tasks, they consistently struggle with…

knowledge editing

Lifelong Knowledge Editing requires Better Regularization

2025-02-03 · Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu, Ahmed Alaa 외

Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing. In this paper, we formalize the popular locate-t…

knowledge editing

EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing

2025-10-11 · Sicheng Lyu, Yu Gu, Xinyu Wang, Jerry Huang 외 arxiv

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 burde…

knowledge editing

Knowledge Editing in Masked Diffusion Language Models

2026-06-02 · Haewon Park, Yohan Jo arxiv

Knowledge editing aims to update or correct factual knowledge in a language model. A widely used approach, locate-then-edit, does this in two steps: it first localizes a fact within the model, then edits the weights ther…

knowledge editing

Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs

2025-10-31 · Jiahao Liu, Zijian Wang, Kuo Zhao, Dong Hu arxiv

Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modifies their parameters. However, most exis…

knowledge editing