Open Access

ARTICLE

AdaptForever: Elastic and Mutual Learning for Continuous NLP Task Mastery

Ke Chen^1,2, Cheng Peng^1,2, Xinyang He^1,2, Jiakang Sun^1,2, Xu Liu^1,2, Xiaolin Qin^1,2,*, Yong Zhong^1,2,*

1 Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, 610213, China
2 University of Chinese Academy of Sciences, Beijing, 101408, China

* Corresponding Authors: Xiaolin Qin. Email: ; Yong Zhong. Email:

(This article belongs to the Special Issue: Advancements in Natural Language Processing (NLP) and Fuzzy Logic)

Computers, Materials & Continua 2025, 82(3), 4003-4019. https://doi.org/10.32604/cmc.2025.057443

Received 17 August 2024; Accepted 10 December 2024; Issue published 06 March 2025

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.

---

Keywords

---