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

Yaxin Zhu, Hamed Zamani


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 Multi-label Learning (ICXML), a two-stage framework that cuts down the search space by generating a set of candidate labels through in-context learning and then reranks them. Extensive experiments suggest that ICXML advances the state of the art on two diverse public benchmarks.
Anthology ID:
2024.findings-naacl.134
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2086–2098
Language:
URL:
https://aclanthology.org/2024.findings-naacl.134
DOI:
10.18653/v1/2024.findings-naacl.134
Bibkey:
Cite (ACL):
Yaxin Zhu and Hamed Zamani. 2024. ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2086–2098, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification (Zhu & Zamani, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.134.pdf