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

TL;DR

This paper introduces a zero-shot hierarchical classification framework using entailment-contradiction prediction with large language models, addressing real-world challenges without requiring parameter updates.

Contribution

It proposes a novel zero-shot hierarchical classification method that leverages entailment-contradiction prediction, improving performance without additional training.

Findings

Strong performance across multiple datasets

Effective in strict zero-shot settings

No parameter updates needed

Abstract

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.