Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification
Chen, Shijing Bouadjenek, Mohamed Reda Naseem, Usman Suleiman, Basem Jameel, Shoaib Salim, Flora Hacid, Hakim Razzak, Imran
Chen, Shijing
Bouadjenek, Mohamed Reda
Naseem, Usman
Suleiman, Basem
Jameel, Shoaib
Salim, Flora
Hacid, Hakim
Razzak, Imran
Supervisor
Department
Computational Biology
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Multi-level Hierarchical Classification (MLHC) tackles the challenge of categorizing items within a complex, multi-layered class structure. However, traditional MLHC classifiers often rely on a backbone model with n independent output layers, which tend to ignore the hierarchical relationships between classes. This oversight can lead to inconsistent predictions that violate the underlying taxonomy. Leveraging Large Language Models (LLMs), we propose novel taxonomy-embedded transitional LLM-agnostic framework for multimodality classification. The cornerstone of this advancement is the ability of models to enforce consistency across hierarchical levels. Our evaluations on the MEP-3M dataset - a Multi-modal E-commerce Product dataset with various hierarchical levels- demonstrated a significant performance improvement compared to conventional LLMs structure. © 2025 Association for Computational Linguistics.
Citation
S. Chen et al., “Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification,” Proceedings - International Conference on Computational Linguistics, COLING, vol. Part, pp. 6244–6254, Jan. 2025.
Source
Proceedings - International Conference on Computational Linguistics, COLING
Conference
Keywords
Multi-level Hierarchical Classification (MLHC), Large Language Models (LLMs), Taxonomy-embedded framework, Multimodal classification, MEP-3M dataset?
Subjects
Source
Publisher
Association for Computational Linguistics