--In recent years, pretrained large language models have demonstrated outstanding performance across various natural language processing tasks. However, full-parameter fine-tuning methods require adjusting all model parameters, leading to immense computational resource demands. Although parameter-efficient fine-tuning methods like LoRA have significantly reduced the number of parameters, they still face challenges such as gradient vanishing and the potential for further parameter reduction. T o address these issues, this paper proposes a novel parameter-efficient fine-tuning method called LoR 2 C (Low-Rank Residual Connection Adaptation). LoR 2 C introduces residual connections with low-rank matrices within the model layers, which not only reduces the number of fine-tuning parameters but also effectively alleviates the gradient vanishing problem. Additionally, this paper presents three optimization variants of LoR 2 C: ShareLoR 2 C, MergeLoR 2 C, and InjectLoR 2 C. These variants further improve parameter efficiency and model performance through parameter sharing, module merging, and injection mechanisms, respectively. I NTRODUCTION In recent years, the scale of large language models (LLM) has grown rapidly and these models have demonstrated exceptional performance on various tasks. However, despite the significant performance improvements that full parameter fine-tuning (FT) can bring, adjusting all the model parameters not only consumes massive computational resources, but also may lead to overfitting and inefficient training. To address these challenges, researchers have proposed Parameter-Efficient Fine-Tuning (PEFT) methods aimed at reducing computational costs while maintaining fine-tuning effectiveness. LoRA [1] emerged in this context.