# Towards Robust Few-Shot Text Classification Using Transformer Architectures and Dual Loss Strategies

arXiv: https://arxiv.org/abs/2505.06145 · HTML: https://mlsanity.com/paper/2505.06145/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 5 of 5)

- [Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification](https://mlsanity.com/paper/2406.08660/) (2024)
- [Mask-guided BERT for Few Shot Text Classification](https://mlsanity.com/paper/2302.10447/) (2023)
- [Social Network User Profiling for Anomaly Detection Based on Graph Neural Networks](https://mlsanity.com/paper/2503.19380/) (2025)
- [Addressing Class Imbalance with Probabilistic Graphical Models and Variational Inference](https://mlsanity.com/paper/2504.05758/) (2025)
- [Contrastive and Variational Approaches in Self-Supervised Learning for Complex Data Mining](https://mlsanity.com/paper/2504.04032/) (2025)

## Built on by (most cited first, 4 of 4)

- [Structured Memory Mechanisms for Stable Context Representation in Large Language Models](https://mlsanity.com/paper/2505.22921/) (2025)
- [Capsule Network-Based Semantic Intent Modeling for Human-Computer Interaction](https://mlsanity.com/paper/2507.00540/) (2025)
- [Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approach](https://mlsanity.com/paper/2508.06155/) (2025)
- [Time-Series Learning for Proactive Fault Prediction in Distributed Systems with Deep Neural Structures](https://mlsanity.com/paper/2505.20705/) (2025)

## Abstract (arXiv)

Few-shot text classification has important application value in low-resource environments. This paper proposes a strategy that combines adaptive fine-tuning, contrastive learning, and regularization optimization to improve the classification performance of Transformer-based models. Experiments on the FewRel 2.0 dataset show that T5-small, DeBERTa-v3, and RoBERTa-base perform well in few-shot tasks, especially in the 5-shot setting, which can more effectively capture text features and improve classification accuracy. The experiment also found that there are significant differences in the classification difficulty of different relationship categories. Some categories have fuzzy semantic boundaries or complex feature distributions, making it difficult for the standard cross entropy loss to learn the discriminative information required to distinguish categories. By introducing contrastive loss and regularization loss, the generalization ability of the model is enhanced, effectively alleviating the overfitting problem in few-shot environments. In addition, the research results show that the use of Transformer models or generative architectures with stronger self-attention mechanisms can help improve the stability and accuracy of few-shot classification.