# Small sample-based adaptive text classification through iterative and contrastive description refinement

arXiv: https://arxiv.org/abs/2508.00957 · HTML: https://mlsanity.com/paper/2508.00957/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 1 Aug 2025.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation](https://mlsanity.com/paper/2406.12114/) (2024)
- [Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach](https://mlsanity.com/paper/2209.06995/) (2022)
- [Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM](https://mlsanity.com/paper/2304.11872/) (2023)
- [Prompt-Learning for Short Text Classification](https://mlsanity.com/paper/2202.11345/) (2022)
- [Active Few-Shot Learning for Text Classification](https://mlsanity.com/paper/2502.18782/) (2025)
- [BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions](https://mlsanity.com/paper/2310.06111/) (2023)
- [PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification](https://mlsanity.com/paper/2305.14963/) (2023)

## Abstract (arXiv)

Zero-shot text classification remains a difficult task in domains with evolving knowledge and ambiguous category boundaries, such as ticketing systems. Large language models (LLMs) often struggle to generalize in these scenarios due to limited topic separability, while few-shot methods are constrained by insufficient data diversity. We propose a classification framework that combines iterative topic refinement, contrastive prompting, and active learning. Starting with a small set of labeled samples, the model generates initial topic labels. Misclassified or ambiguous samples are then used in an iterative contrastive prompting process to refine category distinctions by explicitly teaching the model to differentiate between closely related classes. The framework features a human-in-the-loop component, allowing users to introduce or revise category definitions in natural language. This enables seamless integration of new, unseen categories without retraining, making the system well-suited for real-world, dynamic environments. The evaluations on AGNews and DBpedia demonstrate strong performance: 91% accuracy on AGNews (3 seen, 1 unseen class) and 84% on DBpedia (8 seen, 1 unseen), with minimal accuracy shift after introducing unseen classes (82% and 87%, respectively). The results highlight the effectiveness of prompt-based semantic reasoning for fine-grained classification with limited supervision.