paper-with-me

Papers

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging

2025-10-23 · Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Yifan Gong, Sheng Zhang arxiv

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to historical data. RECALL computes inter-model similarity from layer-wise hidden representations over clustered typical samples, and performs adaptive, hierarchical parameter fusion to align knowledge across models. This design enables the preservation of domain-general features in shallow layers while allowing task-specific adaptation in deeper layers. Unlike prior methods that require task labels or incur performance trade-offs, RECALL achieves seamless multi-domain integration and strong resistance to catastrophic forgetting. Extensive experiments across five NLP tasks and multiple continual learning scenarios show that RECALL outperforms baselines in both knowledge retention and generalization, providing a scalable and data-free solution for evolving LLMs.

📄 PDF Abstract BibTeX arXiv:2510.20479

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Dynamically Addressing Unseen Rumor via Continual Learning

2021-04-18 · Nayeon Lee, Andrea Madotto, Yejin Bang, Pascale Fung

Rumors are often associated with newly emerging events, thus, an ability to deal with unseen rumors is crucial for a rumor veracity classification model. Previous works address this issue by improving the model's general…

Continual LearningVeracity Classification

Towards Training Recurrent Neural Networks for Lifelong Learning

2018-11-16 · Shagun Sodhani, Sarath Chandar, Yoshua Bengio

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emph…

Lifelong learning

Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity

2023-10-26 · Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy 외

Deep reinforcement learning methods exhibit impressive performance on a range of tasks but still struggle on hard exploration tasks in large environments with sparse rewards. To address this, intrinsic rewards can be gen…

Deep Reinforcement LearningPrediction

Do Your Best and Get Enough Rest for Continual Learning

2025-03-24 · CVPR 2025 1 · Hankyul Kang, Gregor Seifer, DongHyun Lee, Jongbin Ryu

According to the forgetting curve theory, we can enhance memory retention by learning extensive data and taking adequate rest. This means that in order to effectively retain new knowledge, it is essential to learn it tho…

Continual LearningIncremental LearningSelf-Supervised Learning

On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-Tuning

2026-03-10 · Muhammad Ahmad, Jingjing Zheng, Yankai Cao arxiv

Parameter-efficient fine-tuning (PEFT) based on low-rank decomposition, such as LoRA, has become a standard for adapting large pretrained models. However, its behavior in sequential learning -- specifically regarding cat…

parameter-efficient fine-tuningContinual Learning