Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.05752 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911255506190336 |
|---|---|
| author | Song, Xiangchen Huang, Yulin Guo, Jinxu Liu, Yuchen Luan, Yaxuan |
| author_facet | Song, Xiangchen Huang, Yulin Guo, Jinxu Liu, Yuchen Luan, Yaxuan |
| contents | This study investigates a hybrid method for text classification that integrates deep feature extraction from large language models, multi-scale fusion through feature pyramids, and structured modeling with graph neural networks to enhance performance in complex semantic contexts. First, the large language model captures contextual dependencies and deep semantic representations of the input text, providing a rich feature foundation for subsequent modeling. Then, based on multi-level feature representations, the feature pyramid mechanism effectively integrates semantic features of different scales, balancing global information and local details to construct hierarchical semantic expressions. Furthermore, the fused features are transformed into graph representations, and graph neural networks are employed to capture latent semantic relations and logical dependencies in the text, enabling comprehensive modeling of complex interactions among semantic units. On this basis, the readout and classification modules generate the final category predictions. The proposed method demonstrates significant advantages in robustness alignment experiments, outperforming existing models on ACC, F1-Score, AUC, and Precision, which verifies the effectiveness and stability of the framework. This study not only constructs an integrated framework that balances global and local information as well as semantics and structure, but also provides a new perspective for multi-scale feature fusion and structured semantic modeling in text classification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Scale Feature Fusion and Graph Neural Network Integration for Text Classification with Large Language Models Song, Xiangchen Huang, Yulin Guo, Jinxu Liu, Yuchen Luan, Yaxuan Computation and Language This study investigates a hybrid method for text classification that integrates deep feature extraction from large language models, multi-scale fusion through feature pyramids, and structured modeling with graph neural networks to enhance performance in complex semantic contexts. First, the large language model captures contextual dependencies and deep semantic representations of the input text, providing a rich feature foundation for subsequent modeling. Then, based on multi-level feature representations, the feature pyramid mechanism effectively integrates semantic features of different scales, balancing global information and local details to construct hierarchical semantic expressions. Furthermore, the fused features are transformed into graph representations, and graph neural networks are employed to capture latent semantic relations and logical dependencies in the text, enabling comprehensive modeling of complex interactions among semantic units. On this basis, the readout and classification modules generate the final category predictions. The proposed method demonstrates significant advantages in robustness alignment experiments, outperforming existing models on ACC, F1-Score, AUC, and Precision, which verifies the effectiveness and stability of the framework. This study not only constructs an integrated framework that balances global and local information as well as semantics and structure, but also provides a new perspective for multi-scale feature fusion and structured semantic modeling in text classification tasks. |
| title | Multi-Scale Feature Fusion and Graph Neural Network Integration for Text Classification with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.05752 |