Structure-Learnable Adapter Fine-Tuning for Parameter-Efficient Large Language Models
By: Ming Gong , Yingnan Deng , Nia Qi and more
Potential Business Impact:
AI learns new tasks without forgetting old ones.
This paper addresses the issues of parameter redundancy, rigid structure, and limited task adaptability in the fine-tuning of large language models. It proposes an adapter-based fine-tuning method built on a structure-learnable mechanism. By introducing differentiable gating functions and structural sparsity control variables, the method enables automatic optimization of adapter insertion points, activation paths, and module combinations. This allows the model to adjust its structure flexibly in multi-task settings to match different task characteristics. With the backbone parameters kept frozen, the method uses a structure search mechanism to guide the dynamic construction of task-specific efficient substructures during training. This significantly improves parameter utilization and representational capacity. In addition, the paper designs a set of sensitivity analysis experiments to systematically evaluate the effects of sparsity weight, noise injection ratio, and data perturbation on model performance. These experiments verify the stability and robustness of the proposed method across various multi-task natural language understanding tasks. The experimental results show that the proposed method outperforms mainstream parameter-efficient tuning techniques on multiple tasks. It achieves a better balance among accuracy, compression rate, and robustness to noise and perturbation.
Similar Papers
Structural Priors and Modular Adapters in the Composable Fine-Tuning Algorithm of Large-Scale Models
Machine Learning (CS)
Helps AI learn many things faster and better.
Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models
Computation and Language
Helps computers understand facts and connect ideas.
Lifelong Learning with Task-Specific Adaptation: Addressing the Stability-Plasticity Dilemma
Machine Learning (CS)
Teaches computers to learn new things without forgetting.