ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification

TL;DR

This paper introduces ICXML, a two-stage in-context learning framework for zero-shot extreme multi-label classification that efficiently narrows down candidate labels and improves performance on benchmark datasets.

Contribution

The paper proposes a novel two-stage framework, ICXML, that leverages in-context learning to address zero-shot XMC challenges and outperforms existing methods.

Findings

ICXML achieves state-of-the-art results on benchmark datasets.

The framework effectively reduces the label search space.

Experimental results demonstrate significant performance improvements.

Abstract

This paper focuses on the task of Extreme Multi-Label Classification (XMC) whose goal is to predict multiple labels for each instance from an extremely large label space. While existing research has primarily focused on fully supervised XMC, real-world scenarios often lack supervision signals, highlighting the importance of zero-shot settings. Given the large label space, utilizing in-context learning approaches is not trivial. We address this issue by introducing In-Context Extreme Multilabel Learning (ICXML), a two-stage framework that cuts down the search space by generating a set of candidate labels through incontext learning and then reranks them. Extensive experiments suggest that ICXML advances the state of the art on two diverse public benchmarks.