Massive Editing for Large Language Models Based on Dynamic Weight Generation
Wentao Wan, Qiqing Lao, Zhiwei Xie, Hefeng Wu, Runnan Lin, Liang Lin, Keze Wang
Abstract
Knowledge Editing (KE) is a field that studies how to modify some knowledge in Large Language Models (LLMs) at a low cost (compared to pre-training). Currently, performing large-scale edits on LLMs while ensuring the Reliability, Generality, and Locality metrics of the edits remain a challenge. This paper proposes a Massive editing approach for LLMs based on dynamic weight Generation (MeG). Our MeG involves attaching a dynamic weight neuron to specific layers of the LLMs and using a diffusion model to conditionally generate the weights of this neuron based on the input query required for the knowledge. This allows the use of adding a single dynamic weight neuron to achieve the goal of large-scale knowledge editing. Experiments show that our MeG can significantly improve the performance of large-scale KE in terms of Reliability, Generality, and Locality metrics compared to existing knowledge editing methods, particularly with a high percentage point increase in the absolute value index for the Locality metric, demonstrating the advantages of our proposed method.
BibTeX
@inproceedings{
wan2026massive,
title={Massive Editing for Large Language Models Based on Dynamic Weight Generation},
author={Wentao Wan and Qiqing Lao and Zhiwei Xie and Hefeng Wu and Runnan Lin and Liang Lin and Keze Wang},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=GJfWu4BjoI}
}