Hierarchical Text Classification Using Black Box Large Language Models
By: Kosuke Yoshimura, Hisashi Kashima
Potential Business Impact:
Lets computers sort texts into categories better.
Hierarchical Text Classification (HTC) aims to assign texts to structured label hierarchies; however, it faces challenges due to data scarcity and model complexity. This study explores the feasibility of using black box Large Language Models (LLMs) accessed via APIs for HTC, as an alternative to traditional machine learning methods that require extensive labeled data and computational resources. We evaluate three prompting strategies -- Direct Leaf Label Prediction (DL), Direct Hierarchical Label Prediction (DH), and Top-down Multi-step Hierarchical Label Prediction (TMH) -- in both zero-shot and few-shot settings, comparing the accuracy and cost-effectiveness of these strategies. Experiments on two datasets show that a few-shot setting consistently improves classification accuracy compared to a zero-shot setting. While a traditional machine learning model achieves high accuracy on a dataset with a shallow hierarchy, LLMs, especially DH strategy, tend to outperform the machine learning model on a dataset with a deeper hierarchy. API costs increase significantly due to the higher input tokens required for deeper label hierarchies on DH strategy. These results emphasize the trade-off between accuracy improvement and the computational cost of prompt strategy. These findings highlight the potential of black box LLMs for HTC while underscoring the need to carefully select a prompt strategy to balance performance and cost.
Similar Papers
Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy
Computation and Language
Helps computers sort information better.
KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification
Computation and Language
Helps computers sort texts into categories better.
Reasoning for Hierarchical Text Classification: The Case of Patents
Computation and Language
Helps computers explain why they choose labels.