# A Simple and Effective Framework for Strict Zero-Shot Hierarchical Classification

arXiv: https://arxiv.org/abs/2305.15282 · HTML: https://mlsanity.com/paper/2305.15282/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://mlsanity.com/paper/2202.07206/) (2022)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [Improving and Simplifying Pattern Exploiting Training](https://mlsanity.com/paper/2103.11955/) (2021)
- [Language Models are Open Knowledge Graphs](https://mlsanity.com/paper/2010.11967/) (2020)
- [Yelp Dataset Challenge: Review Rating Prediction](https://mlsanity.com/paper/1605.05362/) (2016)
- [Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification](https://mlsanity.com/paper/2203.03825/) (2022)
- [HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification](https://mlsanity.com/paper/2204.13413/) (2022)
- [Zero-Shot Text Classification with Self-Training](https://mlsanity.com/paper/2210.17541/) (2022)
- [Exploiting Global and Local Hierarchies for Hierarchical Text Classification](https://mlsanity.com/paper/2205.02613/) (2022)
- [Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning](https://mlsanity.com/paper/2104.01666/) (2021)
- [Making Pretrained Language Models Good Long-tailed Learners](https://mlsanity.com/paper/2205.05461/) (2022)

## Built on by (most cited first, 7 of 7)

- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification](https://mlsanity.com/paper/2406.17534/) (2024)
- [Hierarchical Text Classification with LLM-Refined Taxonomies](https://mlsanity.com/paper/2601.18375/) (2026)
- [Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation](https://mlsanity.com/paper/2410.03829/) (2024)
- [Hierarchical Text Classification Using Black Box Large Language Models](https://mlsanity.com/paper/2508.04219/) (2025)
- [The Advantage of Fine-Grained Training](https://mlsanity.com/paper/2509.05130/) (2025)
- [TEAMMix: Taxonomy Enrichment Augmentation and Minority-augmented Mixing Strategy for LLM-enhanced Weak-Supervised Hierarchical Text Classification](https://mlsanity.com/paper/2608.11044/) (2026)

## Abstract (arXiv)

In recent years, large language models (LLMs) have achieved strong performance on benchmark tasks, especially in zero or few-shot settings. However, these benchmarks often do not adequately address the challenges posed in the real-world, such as that of hierarchical classification. In order to address this challenge, we propose refactoring conventional tasks on hierarchical datasets into a more indicative long-tail prediction task. We observe LLMs are more prone to failure in these cases. To address these limitations, we propose the use of entailment-contradiction prediction in conjunction with LLMs, which allows for strong performance in a strict zero-shot setting. Importantly, our method does not require any parameter updates, a resource-intensive process and achieves strong performance across multiple datasets.