paper-with-me

홈 › Papers

From Static to Dynamic: A Continual Learning Framework for Large Language Models

2023-10-22 · Mingzhe Du, Anh Tuan Luu, Bin Ji, See-Kiong Ng

The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks. However, this complexity also presents challenges, making LLMs difficult to train and inhibiting their ability to continuously assimilate new knowledge, which may lead to inaccuracies in their outputs. To mitigate these issues, this paper presents DynaMind, a novel continual learning framework designed for LLMs. DynaMind incorporates memory mechanisms to assimilate new knowledge and modular operators to enhance the model inference process with the newly assimilated knowledge, consequently improving the accuracies of LLMs' outputs. Benchmark experiments demonstrate DynaMind's effectiveness in overcoming these challenges. The code and demo of DynaMind are available on GitHub: https://github.com/Elfsong/DynaMind.

📄 PDF Abstract BibTeX arXiv:2310.14248

Code (1)

elfsong/dynamind 공식 구현

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

ConPET: Continual Parameter-Efficient Tuning for Large Language Models

2023-09-26 · Chenyang Song, Xu Han, Zheni Zeng, Kuai Li 외

Continual learning necessitates the continual adaptation of models to newly emerging tasks while minimizing the catastrophic forgetting of old ones. This is extremely challenging for large language models (LLMs) with van…

Continual Learning

Dynamic Dialogue Policy for Continual Reinforcement Learning

2022-04-12 · COLING 2022 10 · Christian Geishauser, Carel van Niekerk, Nurul Lubis, Michael Heck 외

Continual learning is one of the key components of human learning and a necessary requirement of artificial intelligence. As dialogue can potentially span infinitely many topics and tasks, a task-oriented dialogue system…

Continual Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Reactivation: Empirical NTK Dynamics Under Task Shifts

2025-07-21 · Yuzhi Liu, Zixuan Chen, Zirui Zhang, Yufei Liu 외 arxiv

The Neural Tangent Kernel (NTK) offers a powerful tool to study the functional dynamics of neural networks. In the so-called lazy, or kernel regime, the NTK remains static during training and the network function is line…

Continual Learning

Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback

2025-05-15 · Yutao Yang, Jie zhou, Junsong Li, Qianjun Pan 외

This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major…

Continual LearningContrastive Learning

Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning

2025-03-20 · Peiyi Lin, Fukai Zhang, Kai Niu, Hao Fu

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting wh…

Continual Learning