paper-with-me

홈 › Papers

Examining Forgetting in Continual Pre-training of Aligned Large Language Models

2024-01-06 · Chen-An Li, Hung-Yi Lee

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common practice involves continual pre-training on previously fine-tuned models. However, this can lead to catastrophic forgetting. In our work, we investigate the phenomenon of forgetting that occurs during continual pre-training on an existing fine-tuned LLM. We evaluate the impact of continuous pre-training on the fine-tuned LLM across various dimensions, including output format, knowledge, and reliability. Experiment results highlight the non-trivial challenge of addressing catastrophic forgetting during continual pre-training, especially the repetition issue.

📄 PDF Abstract BibTeX arXiv:2401.03129

Code (1)

lca0503/llama_tw 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Enhancing Generative Class Incremental Learning Performance with Model Forgetting Approach

2024-03-27 · Taro Togo, Ren Togo, Keisuke Maeda, Takahiro Ogawa 외

This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism, aimed at dynamically managing class information for better adaptation to streaming data. GCIL …

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

2025-02-16 · Gangwei Jiang, Caigao Jiang, Zhaoyi Li, Siqiao Xue 외

Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced capabilities of Large Language Models (LL…

Continual Learning

Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs

2025-11-25 · Ziqi Wang, Chang Che, Qi Wang, Hui Ma 외 arxiv

While continual visual instruction tuning (CVIT) has shown promise in adapting multimodal large language models (MLLMs), existing studies predominantly focus on models without safety alignment. This critical oversight ig…

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning

2023-07-16 · Zhenyi Wang, Enneng Yang, Li Shen, Heng Huang

Forgetting refers to the loss or deterioration of previously acquired knowledge. While existing surveys on forgetting have primarily focused on continual learning, forgetting is a prevalent phenomenon observed in various…

Continual LearningFederated LearningPrivacy PreservingSurvey

Brain-Inspired Continual Learning-Robust Feature Distillation and Re-Consolidation for Class Incremental Learning

2024-04-22 · Hikmat Khan, Nidhal Carla Bouaynaya, Ghulam Rasool

Artificial intelligence (AI) and neuroscience share a rich history, with advancements in neuroscience shaping the development of AI systems capable of human-like knowledge retention. Leveraging insights from neuroscience…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning