用LLM增强标签层次并生成伪样本，解决文本分类中的类别不平衡问题。
TEAMMix: Taxonomy Enrichment Augmentation and Minority-augmented Mixing Strategy for LLM-enhanced Weak-Supervised Hierarchical Text Classification
- 通过关键词和语料挖掘扩充标签语义，增强模型对层级结构的理解。
- 利用高斯混合模型筛选高质量伪样本，使细粒度分类准确率提升12.3%。
- 适合处理长尾分布的细粒度文本分类任务，尤其在标注数据稀缺时有效。
层次化文本分类（HTC）作为关键的文本挖掘任务，面临标签层级复杂和类别不平衡的挑战。基于大语言模型（LLMs）的现有方法因提示过长和标签结构信息丢失等问题，难以高效应用。本文提出一种由LLM增强的弱监督HTC框架，首先通过关键词生成与语料挖掘对标签层级进行语义扩充，提升模型对标签的理解；随后引导LLM生成伪样本以缓解长尾问题，并采用高斯混合模型进行置信度驱动的重采样，优化生成数据质量。实验表明，该方法显著提升了LLM生成伪标签的可靠性，在细粒度且不平衡的数据集上分类性能得到明显改善。
原文摘要 · Abstract (English)
Hierarchical Text Classification (HTC), as a critical text mining task, faces challenges such as complex label hierarchies and class imbalance. Existing methods based on large language models (LLMs) struggle to be efficiently applied to this task due to issues like lengthy prompts and loss of label structural information. To address these limitations, this paper proposes a weakly supervised HTC framework enhanced by LLM-based data augmentation. The framework first enriches the label hierarchy semantically through keyword generation and corpus mining, thereby enhancing the model's understanding of labels. Subsequently, it guides the LLM to generate pseudo-samples to mitigate the long-tail problem, and employs a Gaussian mixture model for confidence-based resampling to optimize the quality of generated data. Experimental results demonstrate that the proposed method effectively improves the reliability of LLM-generated pseudo-labels and significantly enhances classification performance on fine-grained and imbalanced datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。