MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation (opens in new tab)

Pre-trained language models struggle when applied to new domains, as full fine-tuning is computationally expensive and prone to catastrophic forgetting. This study addresses this challenge by presenting a novel parameter-efficient strategy for unsupervised domain adaptation that combines custom PEFT architectures with mixed-objective training. Our approach simultaneously optimizes classification performance on labeled source domain data and ma...