Effective In-Context Example Selection through Data Compression

Autor:	Sun, Zhongxiang, Zhang, Kepu, Wang, Haoyu, Zhang, Xiao, Xu, Jun
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by ACL 2024 finding
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.11465 Zobrazit plný text záznamu View this record from Arxiv