Improving optimal prompt learning through multilayer fusion and latent dirichlet allocation.

Abstract

Recent advances in few-shot learning have demonstrated the potential of prompt-based techniques with pre-trained models, eliminating the need for extensive fine-tuning. However, challenges such as obtaining optimal prompts and addressing data scarcity in specialized domains remain challenging. We introduce a novel framework incorporating a Global Attention Mechanism (GAM) that effectively integrates features from multiple layers of pre-trained language models, enhanced by Latent Dirichlet Allocation (LDA) generated topic features for prompt optimization. Extensive experiments on four datasets consistently show that our approach outperforms state of-the-art baselines. The strategic integration of GAM with layer-specific features and LDA topics proves particularly effective in extracting valuable latent information for few-shot learning scenarios, yielding significant improvements in specialized domains, as evidenced by enhanced performance in therapeutic dialogue classification within a Applied Behavior Analysis clinical dataset.