TARDiS : Text Augmentation for Refining Diversity and Separability
This addresses the challenge of improving text classification performance in few-shot settings, though it appears incremental as it builds on existing two-stage TA methods.
The paper tackled the problem of limited diversity and separability in text augmentation for few-shot text classification by introducing TARDiS, a novel LLM-based method with generation and alignment stages, which outperformed state-of-the-art methods in various tasks.
Text augmentation (TA) is a critical technique for text classification, especially in few-shot settings. This paper introduces a novel LLM-based TA method, TARDiS, to address challenges inherent in the generation and alignment stages of two-stage TA methods. For the generation stage, we propose two generation processes, SEG and CEG, incorporating multiple class-specific prompts to enhance diversity and separability. For the alignment stage, we introduce a class adaptation (CA) method to ensure that generated examples align with their target classes through verification and modification. Experimental results demonstrate TARDiS's effectiveness, outperforming state-of-the-art LLM-based TA methods in various few-shot text classification tasks. An in-depth analysis confirms the detailed behaviors at each stage.