SwitchCIT：用于持续指令微调的切换机制
SwitchCIT: Switching for Continual Instruction Tuning
AI总结：
本文提出SwitchCIT方法，通过一种将计算路由到参数高效微调模型的切换机制，有效解决大型模型在持续指令微调中的灾难性遗忘问题，并在多任务实验中展现出高效、可扩展和隐私保护等优势。
摘要：
大型语言模型（LLMs）和多模态模型在各个领域展现出了令人印象深刻的能力，特别是在通用语言理解和视觉推理方面。然而，这些在大量数据上训练的模型，可能并未针对由指令触发的特定任务进行精细优化。持续指令微调对于使大型模型适应不断演变的任务和领域至关重要，可确保其在广泛的应用中的有效性和相关性。在持续指令微调的背景下，模型在不同任务上按顺序训练，可能会发生灾难性遗忘，导致在先前学习的任务上性能下降。这项工作通过一种切换机制，将计算路由到参数高效微调的模型，来解决持续指令学习中的灾难性遗忘问题。我们通过对不同自然语言生成任务和视觉语言任务进行持续指令微调的实验，证明了我们方法的有效性。我们还展示了我们提出的方法在效率、可扩展性、可移植性和隐私保护方面的优势。
英文摘要：
Large language models (LLMs) and multimodal models (MMs) have exhibited impressive capabilities in various domains, particularly in general language understanding and visual reasoning. However, these models, trained on massive data, may not be finely optimized for specific tasks triggered by instructions. Continual instruction tuning is crucial to adapt a large model to evolving tasks and domains, ensuring their effectiveness and relevance across a wide range of applications. In the context of continual instruction tuning, where models are sequentially trained on different tasks, catastrophic forgetting can occur, leading to performance degradation on previously learned tasks. This work addresses the catastrophic forgetting in continual instruction learning through a switching mechanism for routing computations to parameter-efficient tuned models. We demonstrate the effectiveness of our method through experiments on continual instruction tuning of different natural language generation tasks and vision-language tasks. We also showcase the advantages of our proposed method in terms of efficiency, scalability, portability, and privacy preservation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
