most citedTowards Effective and Efficient Continual Pre-training of Large Language Models

2 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2024

Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning

Kaiyi Zhang, Ang Lv, Yuhan Chen +3

In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples. This understanding leads us to…