@misc{chen2026multihead,
title = {Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers},
author = {Anrui Chen and Ruijun Huang and Xin Zhang and Fang Dong and Hengjie Cao and Zhen-Dong Huang and Yifeng Yang and Mengyi Chen and Jixian Zhou and Mingzhi Dong and Yujiang Wang and Jinlong Hou and Qin Lv and Robert P. Dick and Yuan Cheng and Tun Lu and Fan Yang and Li Shang},
year = {2026},
eprint = {2602.12587},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2602.12587},
}