Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting

Qin, Zhen; Jagerman, Rolf; Hui, Kai; Zhuang, Honglei; Wu, Junru; Yan, Le; Shen, Jiaming; Liu, Tianqi; Liu, Jialu; Metzler, Donald; Wang, Xuanhui; Bendersky, Michael

doi:10.18653/v1/2024.findings-naacl.97

articleJan 1, 2024GOLD OA

Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting

ZQZhen Qin RJRolf Jagerman KHKai Hui HZHonglei Zhuang JWJunru Wu

Google (United States)

Indexed incrossref

Abstract

Zhen Qin, Rolf Jagerman, Kai Hui, Honglei Zhuang, Junru Wu, Le Yan, Jiaming Shen, Tianqi Liu, Jialu Liu, Donald Metzler, Xuanhui Wang, Michael Bendersky. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.

Citation impact

118

total citations

FWCI: 36.19
Percentile: 100%
References: 0

Citations per year

Authors

12

Topics & keywords

Topics

Keywords

Computer science
Pairwise comparison
Natural language processing
Ranking (information retrieval)
Artificial intelligence
Language model

No related works found for this paper.