# Multi-Scale Feature Fusion and Graph Neural Network Integration for Text Classification with Large Language Models

arXiv: https://arxiv.org/abs/2511.05752 · HTML: https://mlsanity.com/paper/2511.05752/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Synthesizer: Rethinking Self-Attention in Transformer Models](https://mlsanity.com/paper/2005.00743/) (2020)
- [Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models](https://mlsanity.com/paper/2510.01231/) (2025)
- [Structure-Learnable Adapter Fine-Tuning for Parameter-Efficient Large Language Models](https://mlsanity.com/paper/2509.03057/) (2025)
- [Dynamic Prompt Fusion for Multi-Task and Cross-Domain Adaptation in LLMs](https://mlsanity.com/paper/2509.18113/) (2025)
- [Structural Generalization for Microservice Routing Using Graph Neural Networks](https://mlsanity.com/paper/2510.15210/) (2025)
- [Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems](https://mlsanity.com/paper/2510.10109/) (2025)
- [TextRGNN: Residual Graph Neural Networks for Text Classification](https://mlsanity.com/paper/2112.15060/) (2021)
- [A semantic hierarchical graph neural network for text classification](https://mlsanity.com/paper/2209.07031/) (2022)

## Built on by (most cited first, 2 of 2)

- [Structure-Aware Decoding Mechanisms for Complex Entity Extraction with Large-Scale Language Models](https://mlsanity.com/paper/2512.13980/) (2025)
- [Coordinated Semantic Alignment and Evidence Constraints for Retrieval-Augmented Generation with Large Language Models](https://mlsanity.com/paper/2603.04647/) (2026)

## Abstract (arXiv)

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.