ReflectivePrompt: Reflective evolution in autoprompting algorithms

TL;DR

ReflectivePrompt introduces an evolutionary autoprompting method that employs reflective evolution to improve prompt optimization for large language models, achieving significant performance gains across multiple datasets.

Contribution

It presents a novel reflective evolution approach for autoprompting, enhancing prompt search precision and incorporating knowledge accumulation during evolution.

Findings

Achieves an average 28% improvement on BBH dataset.

Outperforms current state-of-the-art autoprompting methods.

Effective across classification and text generation tasks.

Abstract

Autoprompting is the process of automatically selecting optimized prompts for language models, which has been gaining popularity with the rapid advancement of prompt engineering, driven by extensive research in the field of large language models (LLMs). This paper presents ReflectivePrompt - a novel autoprompting method based on evolutionary algorithms that employs a reflective evolution approach for more precise and comprehensive search of optimal prompts. ReflectivePrompt utilizes short-term and long-term reflection operations before crossover and elitist mutation to enhance the quality of the modifications they introduce. This method allows for the accumulation of knowledge obtained throughout the evolution process and updates it at each epoch based on the current population. ReflectivePrompt was tested on 33 datasets for classification and text generation tasks using open-access large language models: t-lite-instruct-0.1 and gemma3-27b-it. The method demonstrates, on average, a significant improvement (e.g., 28% on BBH compared to EvoPrompt) in metrics relative to current state-of-the-art approaches, thereby establishing itself as one of the most effective solutions in evolutionary algorithm-based autoprompting.