UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation

arXiv:2405.01022v1 Announce Type: new
Abstract: Although pre-trained language models have exhibited great flexibility and versatility with prompt-based few-shot learning, they suffer from the extensive parameter size and limited applicability for inference. Recent studies have suggested that PLMs be used as dataset generators and a tiny task-specific model be trained to achieve efficient inference. However, their applicability to various domains is limited because they tend to generate domain-specific datasets. In this work, we propose a novel approach to universal domain generalization …

abstract arxiv classification cs.ai cs.cl dataset dataset generation domain few-shot few-shot learning flexibility generators inference language language models prompt sentiment studies type universal via zero-shot