cs.CLNov 9, 2026

Path-Level Structural and Semantic Alignment for Hierarchical Multi-Label Text Classification

Authors: Xindi Wang, Aifen Xiong, Baiyang Wang, Xuri Ge, Robert Mercer, Frank Rudzicz, Yifan Peng, Zhumin Chen, 

Organizations: School of Artificial Intelligence, Shandong University, Jinan, China · School of Information Science and Engineering, Shandong University, Qingdao, China · Department of Computer Science, Western University, London, Ontario, Canada · Faculty of Computer Science, Dalhousie University, Halifax, Nova Scotia, Canada · 

Abstract

Hierarchical multi-label text classification (HMTC) requires models to capture both structural dependencies among labels and the fine-grained semantics of labels at different hierarchy levels. Existing methods often model hierarchy through prediction constraints or representations of individual labels and local relations. Structural and semantic supervision, however, are usually formulated separately. We instead use complete root-to-node label paths as a shared unit for both. Our framework introduces two auxiliary training objectives while retaining a standard multi-label classifier at inference. PathSimNCE aligns document representations with hierarchical paths using hierarchy-aware contrastive targets. These targets provide graded supervision for structurally related paths while preserving explicit supervision for the ground-truth paths. The complementary semantic objective uses LLM-generated, document-conditioned descriptions of the same positive paths. It thereby provides context-specific label semantics beyond static label representations. Experiments on three benchmarks show consistent improvements: structural alignment is particularly beneficial in deeper hierarchies, while semantic alignment provides additional gains for fine-grained labels.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MAPLE: Multi-Path Adaptive Propagation with Level-Aware Embeddings for Hierarchical Multi-Label Image Classification

    Mar 31, 2026Boshko Koloski, Marjan Stoimchev, Jurica Levatić +2hierarchical multi-label classificationHierarchical Classification

  2. LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification

    Sep 11, 2026Hui Ye, Jing Zhang, Xiulong Yang +1Late FusionMulti-Label Classification

  3. HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification

    Mar 12, 2026Marjan Stoimchev, Boshko Koloski, Jurica Levatić +2hierarchical multi-label classificationMulti-Label Classification