Speciality vs Generality: An Empirical Study on Catastrophic Forgetting in Fine-tuning Foundation Models

Authors:
  • YLYong Lin
    Yong Lin
  • LTLu Tan
    Lu Tan
  • HLHangyu Lin
    Hangyu Lin
  • ZZZeming Zheng
    Zeming Zheng
  • RPRenjie Pi
    Renjie Pi
  • JZJipeng Zhang
    Jipeng Zhang
  • SDShizhe Diao
    Shizhe Diao
  • HWHaoxiang Wang
    Haoxiang Wang
  • HZHan Zhao
    Han Zhao
  • YYYuan Yao
    Yuan Yao
  • TZTong Zhang
    Tong Zhang

Abstract
Foundation models, including Vision Language Models (VLMs) and Large Language Models (LLMs), possess the $generality$ to handle diverse distributions and tasks, which stems from their extensive pre-training datasets. The fine-tuning of foundation models is a common practice to enhance task performance or align the model's behavior with human expectations, allowing them to gain $speciality$. However, the small datasets used for fine-tuning may not adequately cover the diverse distributions and tasks encountered during pre-training. Consequently, the pursuit of speciality during fine-tuning can lead to a loss of {generality} in the model, which is related to catastrophic forgetting (CF) in deep learning. In this study, we demonstrate this phenomenon in both VLMs and LLMs. For instance, fine-tuning VLMs like CLIP on ImageNet results in a loss of generality in handling diverse distributions, and fine-tuning LLMs like Galactica in the medical domain leads to a loss in following instructions and common sense. To address the trade-off between the speciality and generality, we investigate multiple regularization methods from continual learning, the weight averaging method (Wise-FT) from out-of-distributional (OOD) generalization, which interpolates parameters between pre-trained and fine-tuned models, and parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA). Our findings show that both continual learning and Wise-ft methods effectively mitigate the loss of generality, with Wise-FT exhibiting the strongest performance in balancing speciality and generality.