<ul><li>The in-context learning paradigm with Large Language Models (LLMs) has been crucial for advancing various natural language processing tasks.</li><li>Exemplar selection is important for constructing effective prompts within context-length budget constraints, and it is formulated as a top-m best arms identification problem.</li><li>A new sample-efficient selective exploration strategy called Challenger Arm Sampling for Exemplar selection (CASE) is proposed to reduce sample complexity in exemplar selection tasks.</li><li>CASE achieves up to a 7x speedup in runtime, requires 7x fewer LLM calls, and provides an 87% reduction compared to existing exemplar selection methods, without compromising performance.</li></ul>

Sample Efficient Demonstration Selection for In-Context Learning

Discover more