Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space

TL;DR

This paper introduces a structured prompt optimization framework that enhances few-shot text classification by improving semantic clarity and label alignment through latent space manipulation and semantic factor disentanglement.

Contribution

It proposes a novel structured prompt method with semantic factors and label alignment mechanisms to address semantic entanglement and label ambiguity in low-resource text classification.

Findings

Significant improvements in accuracy, precision, recall, and AUC.

Enhanced robustness and stability across different experimental conditions.

Effective alleviation of semantic conflicts and label ambiguity.

Abstract

This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured prompts to enhance semantic understanding and task adaptation under low-resource conditions. The framework first uses a pretrained language model to encode the input text and obtain basic semantic representations. It then introduces structured prompts composed of multi-dimensional semantic factors and integrates them with text features through a learnable combination mechanism, which forms task-related representations with clear boundaries in the latent space. To further strengthen the consistency between text representations and label semantics, the method constructs a structured label embedding matrix and employs a cross-space alignment mechanism to ensure stable matching between textual features and label attributes. In addition, the model applies prompt orthogonality constraints and a joint optimization objective to maintain independence across different semantic factors in the prompts, allowing the structured prompts to provide transparent and controllable guidance for classification decisions. Three types of sensitivity experiments, including learning rate sensitivity, prompt length sensitivity, and data scale sensitivity, are designed to evaluate the stability and robustness of the framework under different conditions. Experimental results show that the proposed structured prompt optimization framework effectively alleviates semantic conflicts and label ambiguity in few-shot text classification. It significantly improves performance on accuracy, precision, recall, and AUC, and demonstrates strong cross-task applicability.