Advancing Parameter Efficiency in Fine-tuning via Representation Editing

arXiv:2402.15179v1 Announce Type: new
Abstract: Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters. Despite the promising performance of current PEFT methods, they present challenges in hyperparameter selection, such as determining the rank of LoRA or Adapter, or specifying the length of soft prompts. In addressing these challenges, we propose a novel approach to fine-tuning neural models, termed Representation EDiting (RED), which scales and biases …

abstract arxiv attention challenges cs.cl cs.lg current editing efficiency fine-tuning hyperparameter lora parameters peft performance representation results small type via