SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models.

Weixiang Zhao Shilong Wang 0003 Yulin Hu Yanyan Zhao Bing Qin 0001 Xuanyu Zhang Qing Yang 0033 Dongliang Xu Wanxiang Che SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models. 11641-11661 2024 ACL (1) https://doi.org/10.18653/v1/2024.acl-long.625 https://aclanthology.org/2024.acl-long.625 conf/acl/2024-1 db/conf/acl/acl2024-1.html#ZhaoWHZQZYXC24