Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?

Understand

Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning.

• ICL has gained popularity recently with the advent of LLMs due to its simplicity and sample efficiency.
• Prior research has conducted only limited investigation into how these approaches work for multilingual few-shot learning, and the focus so far has been mostly on their performance.
• In this work, we present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, three different NLU tasks, and a myriad of language and domain setups.