Large Language Models (LLMs) have demonstrated significant potential in
performing multiple tasks in multimedia applications, ranging from content
generation to interactive entertainment, and artistic creation. However, the
diversity of downstream tasks in multitask scenarios presents substantial
adaptation challenges for LLMs. While traditional methods often succumb to
knowledge confusion on their monolithic dense models, Mixture-of-Experts (MoE)
has been emerged as a promising solution with its sparse architecture for
effective task decoupling. Inspired by the principles of human cognitive
neuroscience, we design a novel framework \texttt{Intuition-MoR1E} that
leverages the inherent semantic clustering of instances to mimic the human
brain to deal with multitask, offering implicit guidance to router for
optimized feature allocation. Moreover, we introduce cutting-edge Rank-1
Experts formulation designed to manage a spectrum of intuitions, demonstrating
enhanced parameter efficiency and effectiveness in multitask LLM finetuning.
Extensive experiments demonstrate that Intuition-MoR1E achieves superior
efficiency and 2.15\% overall accuracy improvement across 14 public datasets
against other state-of-the-art baselines.

多任务场景下，大型语言模型（LLMs）面临着适应性挑战，而《混合专家模型》（MoE）以其稀疏架构有效地解耦任务而成为一种有希望的解决方案。本研究设计了一种模仿人类大脑的新框架《Intuition-MoR1E》，利用实例的内在语义聚类处理多任务情境，为优化特征分配提供了隐含指导。此外，引入了先进的《Rank-1 专家公式》来管理一系列直觉，在多任务 LLM 微调中表现出增强的参数效率和效果。广泛的实验证明，《Intuition-MoR1E》在 14 个公共数据集上相对于其他最先进方法具备更高的效率和 2.15％的整体准确度提升。