Hierarchical Text Classification Using Black Box Large Language Models

• URL: http://arxiv.org/abs/2508.04219v1
• Date: Wed, 06 Aug 2025 08:53:50 GMT
• Title: Hierarchical Text Classification Using Black Box Large Language Models
• Authors: Kosuke Yoshimura, Hisashi Kashima,
• Abstract summary: Hierarchical Text Classification aims to assign texts to structured label hierarchies.<n>This study explores the feasibility of using black box Large Language Models accessed via APIs for HTC.
• Score: 21.919003715442074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features [57.34477506004105]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>We introduce novel methodologies and datasets to overcome these challenges.<n>We propose MhBART, an encoder-decoder model designed to emulate human writing style.<n>We also propose DTransformer, a model that integrates discourse analysis through PDTB preprocessing to encode structural features.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability [53.51560766150442]
  Critical tokens are elements within reasoning trajectories that significantly influence incorrect outcomes.<n>We present a novel framework for identifying these tokens through rollout sampling.<n>We show that identifying and replacing critical tokens significantly improves model accuracy.
  arXiv  Detail & Related papers  (2024-11-29T18:58:22Z)
• Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data [54.934578742209716]
  In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets.<n>LLKD is an adaptive sample selection method that incorporates signals from both the teacher and student.<n>Our comprehensive experiments show that LLKD achieves superior performance across various datasets with higher data efficiency.
  arXiv  Detail & Related papers  (2024-11-12T18:57:59Z)
• Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification [13.320591504692574]
  We study the HTC problem under a few-shot setting to adapt knowledge in PLMs from an unstructured manner to the downstream hierarchy. We use a simple yet effective method named Hierarchical Conditional Iterative Random Field (HierICRF) to search the most domain-challenging directions. We show that prompt with HierICRF significantly boosts the few-shot HTC performance with an average Micro-F1 by 28.80% to 1.50% and Macro-F1 by 36.29% to 1.5%.
  arXiv  Detail & Related papers  (2024-07-12T03:21:57Z)
• Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification [34.06292178703825]
  We introduce the first ICL-based framework with large language models (LLMs) for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. We can achieve state-of-the-art results in few-shot HTC.
  arXiv  Detail & Related papers  (2024-06-25T13:19:41Z)
• HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification [19.12354692458442]
  Hierarchical text classification (HTC) is a complex subtask under multi-label text classification. We propose HiGen, a text-generation-based framework utilizing language models to encode dynamic text representations.
  arXiv  Detail & Related papers  (2024-01-24T04:44:42Z)
• Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification [10.578682558356473]
  hierarchical text classification (HTC) suffers a poor performance when low-resource or few-shot settings are considered. In this work, we propose the hierarchical verbalizer ("HierVerb"), a multi-verbalizer framework treating HTC as a single- or multi-label classification problem. In this manner, HierVerb fuses label hierarchy knowledge into verbalizers and remarkably outperforms those who inject hierarchy through graph encoders.
  arXiv  Detail & Related papers  (2023-05-26T12:41:49Z)
• HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification [45.314357107687286]
  We propose HPT, a Hierarchy-aware Prompt Tuning method to handle HTC from a multi-label perspective. Specifically, we construct dynamic virtual template and label words which take the form of soft prompts to fuse the label hierarchy knowledge. Experiments show HPT achieves the state-of-the-art performances on 3 popular HTC datasets.
  arXiv  Detail & Related papers  (2022-04-28T11:22:49Z)
• HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization [75.45291796263103]
  The current state-of-the-art model HiAGM for hierarchical text classification has two limitations. It correlates each text sample with all labels in the dataset which contains irrelevant information. We propose HTCInfoMax to address these issues by introducing information which includes two modules.
  arXiv  Detail & Related papers  (2021-04-12T06:04:20Z)
• Data-to-text Generation with Macro Planning [61.265321323312286]
  We propose a neural model with a macro planning stage followed by a generation stage reminiscent of traditional methods. Our approach outperforms competitive baselines in terms of automatic and human evaluation.
  arXiv  Detail & Related papers  (2021-02-04T16:32:57Z)
• DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks [88.62288327934499]
  We propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2020-11-03T07:49:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.