The Butterfly Effect of Model Editing: Few Edits Can Trigger Large
Language Models Collapse

v1v2v3v4 (latest)

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse

15 February 2024

ArXiv (abs)PDF HTML

Papers citing "The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse"

5 / 5 papers shown

Title
Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing Zeping Yu Sophia Ananiadou KELM 101 3 0 24 Jan 2025
Keys to Robust Edits: from Theoretical Insights to Practical Advances Jianhao Yan Futing Wang Yun Luo Yafu Li Yue Zhang KELM 85 0 0 12 Oct 2024
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning Hao Ma Tianyi Hu Zhiqiang Pu Boyin Liu Xiaolin Ai Yanyan Liang Min Chen 163 6 0 08 Oct 2024
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models Sihang Li Houcheng Jiang Kun Wang Yunshan Ma Shi Jie Xiangnan He Tat-Seng Chua Tat-seng Chua KELM 150 66 0 03 Oct 2024
Perturbation-Restrained Sequential Model Editing Junjie Ma Hong Wang Haoyang Xu Zhen-Hua Ling Jia-Chen Gu KELM 135 11 0 27 May 2024