# Text Classification in the LLM Era -- Where do we stand?

arXiv: https://arxiv.org/abs/2502.11830 · HTML: https://mlsanity.com/paper/2502.11830/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2025.

## Built on by (most cited first, 10 of 10)

- [Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?](https://mlsanity.com/paper/2505.18215/) (2025)
- [Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals](https://mlsanity.com/paper/2505.13972/) (2025)
- [AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache](https://mlsanity.com/paper/2510.25979/) (2025)
- [From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification](https://mlsanity.com/paper/2609.01564/) (2026)
- [Benchmarking System One decision models against trained classifiers and language models for automated decision gates](https://mlsanity.com/paper/2610.00346/) (2026)
- [OpenAutoNLU: Open Source AutoML Library for NLU](https://mlsanity.com/paper/2603.01824/) (2026)
- [Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?](https://mlsanity.com/paper/2603.28553/) (2026)
- [Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text](https://mlsanity.com/paper/2605.29076/) (2026)
- [ModTGCN: Modularity-aware Graph Neural Networks for Text Classification](https://mlsanity.com/paper/2606.23694/) (2026)
- [Unified Semantic Modeling Framework for Large-Scale Job Understanding at LinkedIn](https://mlsanity.com/paper/2607.24783/) (2026)

## Abstract (arXiv)

Large Language Models revolutionized NLP and showed dramatic performance improvements across several tasks. In this paper, we investigated the role of such language models in text classification and how they compare with other approaches relying on smaller pre-trained language models. Considering 32 datasets spanning 8 languages, we compared zero-shot classification, few-shot fine-tuning and synthetic data based classifiers with classifiers built using the complete human labeled dataset. Our results show that zero-shot approaches do well for sentiment classification, but are outperformed by other approaches for the rest of the tasks, and synthetic data sourced from multiple LLMs can build better classifiers than zero-shot open LLMs. We also see wide performance disparities across languages in all the classification scenarios. We expect that these findings would guide practitioners working on developing text classification systems across languages.