The Power of Adaptation: Boosting In-Context Learning through Adaptive Prompting

TL;DR

This paper introduces Adaptive-Prompt, a method that adaptively selects exemplars for in-context learning by leveraging model feedback, significantly improving LLM reasoning performance over traditional non-adaptive methods.

Contribution

The paper proposes a novel adaptive exemplar selection method that uses model feedback to enhance in-context learning, addressing redundancy issues in traditional selection strategies.

Findings

Adaptive-Prompt improves reasoning accuracy across multiple tasks.

Adaptive exemplar selection reduces redundancy and increases informativeness.

Experimental results show significant performance gains.

Abstract

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is in-context learning, which encourages a step-by-step reasoning process by including explanatory examples to guide the model's responses. However, selecting appropriate exemplars for the model poses a challenge, as each dataset demands a distinct set of exemplars to enable the LLM to learn effectively and perform well on the test set. Current studies often rely on uncertainty- or diversity-based selection strategies to select exemplars for annotation and to improve model learning. However, these studies typically employ a non-adaptive approach, selecting a set of exemplars all at once. We argue that this non-adaptive strategy may result in a set of exemplars with high redundancy in terms of the knowledge covered, ultimately reducing their overall informativeness. To address this limitation, we propose \textsc{Adaptive-Prompt}, a novel method that adaptively selects exemplars by leveraging model feedback from previously chosen exemplars. Experimental results show that \textsc{Adaptive-Prompt} significantly enhances LLM performance across a variety of reasoning tasks.