ACL 2024findings1 citations
Effective In-Context Example Selection through Data Compression
ZhongXiang Sun, Kepu Zhang, Haoyu Wang, Xiao Zhang, Jun Xu
Abstract
In-context learning has been extensively validated in large language models. However, the mechanism and selection strategy for in-context example selection, which is a crucial ingredient in this approach, lacks systematic and in-depth research. In this paper, we propose a data compression approach to the selection of in-context examples. We introduce a two-stage method that can effectively choose relevant examples and retain sufficient information about the training dataset within the in-context examples. Our method shows a significant improvement of an average of 5.90% across five different real-world datasets using four language models.
BibTeX
@inproceedings{sun-etal-2024-effective,
title = "Effective In-Context Example Selection through Data Compression",
author = "Sun, ZhongXiang and
Zhang, Kepu and
Wang, Haoyu and
Zhang, Xiao and
Xu, Jun",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.50/",
doi = "10.18653/v1/2024.findings-acl.50",
pages = "871--877"
}