@Article{cmc.2025.057443,
AUTHOR = {Ke Chen, Cheng Peng, Xinyang He, Jiakang Sun, Xu Liu, Xiaolin Qin, Yong Zhong},
TITLE = {AdaptForever: Elastic and Mutual Learning for Continuous NLP Task Mastery},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {82},
YEAR = {2025},
NUMBER = {3},
PAGES = {4003--4019},
URL = {http://www.techscience.com/cmc/v82n3/59874},
ISSN = {1546-2226},
ABSTRACT = {In natural language processing (NLP), managing multiple downstream tasks through fine-tuning pre-trained models often requires maintaining separate task-specific models, leading to practical inefficiencies. To address this challenge, we introduce AdaptForever, a novel approach that enables continuous mastery of NLP tasks through the integration of elastic and mutual learning strategies with a stochastic expert mechanism. Our method freezes the pre-trained model weights while incorporating adapters enhanced with mutual learning capabilities, facilitating effective knowledge transfer from previous tasks to new ones. By combining Elastic Weight Consolidation (EWC) for knowledge preservation with specialized regularization terms, AdaptForever successfully maintains performance on earlier tasks while acquiring new capabilities. Experimental results demonstrate that AdaptForever achieves superior performance across a continuous sequence of NLP tasks compared to existing parameter-efficient methods, while effectively preventing catastrophic forgetting and enabling positive knowledge transfer between tasks.},
DOI = {10.32604/cmc.2025.057443}
}