Hierarchical text classification and its foundations: A review of current research

A Zangari, M Marcuzzo, M Rizzo, L Giudice, A Albarelli… - Electronics, 2024‏ - mdpi.com
While collections of documents are often annotated with hierarchically structured concepts,
the benefits of these structures are rarely taken into account by classification techniques …

Retrieval-style in-context learning for few-shot hierarchical text classification

H Chen, Y Zhao, Z Chen, M Wang, L Li… - Transactions of the …, 2024‏ - direct.mit.edu
Hierarchical text classification (HTC) is an important task with broad applications, and few-
shot HTC has gained increasing interest recently. While in-context learning (ICL) with large …

Prompt-based learning framework for zero-shot cross-lingual text classification

K Feng, L Huang, K Wang, W Wei, R Zhang - Engineering Applications of …, 2024‏ - Elsevier
Cross-lingual text classification is a challenging task that aims to train classifiers with data in
one language, known as the source language, and apply the acquired knowledge to data in …

Meta in-context learning makes large language models better zero and few-shot relation extractors

G Li, P Wang, J Liu, Y Guo, K Ji, Z Shang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Relation extraction (RE) is an important task that aims to identify the relationships between
entities in texts. While large language models (LLMs) have revealed remarkable in-context …

Recall, retrieve and reason: towards better in-context relation extraction

G Li, P Wang, W Ke, Y Guo, K Ji, Z Shang, J Liu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Relation extraction (RE) aims to identify relations between entities mentioned in texts.
Although large language models (LLMs) have demonstrated impressive in-context learning …

Prompt-based label-aware framework for few-shot multi-label text classification

T Thaminkaew, P Lertvittayakumjorn, P Vateekul - IEEE Access, 2024‏ - ieeexplore.ieee.org
Prompt-based learning has demonstrated remarkable success in few-shot text classification,
outperforming the traditional fine-tuning approach. This method transforms a text input into a …

A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification

J Zhou, L Zhang, Y He, R Fan, L Zhang… - Proceedings of the 31st …, 2025‏ - aclanthology.org
Hierarchical text classification (HTC) is an important task in natural language processing
(NLP). Existing methods typically utilize both text features and the hierarchical structure of …

Dual prompt tuning based contrastive learning for hierarchical text classification

S **ong, Y Zhao, J Zhang, L Mengxiang… - Findings of the …, 2024‏ - aclanthology.org
Hierarchical text classification aims at categorizing texts into a multi-tiered tree-structured
hierarchy of labels. Existing methods pay more attention to capture hierarchy-aware text …

[HTML][HTML] SPIRIT: Structural Entropy Guided Prefix Tuning for Hierarchical Text Classification

H Zhu, J **a, R Liu, B Deng - Entropy, 2025‏ - mdpi.com
Hierarchical text classification (HTC) is a challenging task that requires classifiers to solve a
series of multi-label subtasks considering hierarchical dependencies among labels. Recent …

Revisiting Hierarchical Text Classification: Inference and Metrics

R Plaud, M Labeau, A Saillenfest, T Bonald - arxiv preprint arxiv …, 2024‏ - arxiv.org
Hierarchical text classification (HTC) is the task of assigning labels to a text within a
structured space organized as a hierarchy. Recent works treat HTC as a conventional …