ReflectivePrompt: Reflective evolution in autoprompting algorithms
By: Viktor N. Zhuravlev , Artur R. Khairullin , Ernest A. Dyagin and more
Potential Business Impact:
Finds best computer instructions for better results.
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.
Similar Papers
Automatic Prompt Optimization with Prompt Distillation
Computation and Language
Makes AI understand tasks better with smart instructions.
Automatic Prompt Optimization with Prompt Distillation
Computation and Language
Teaches computers to write better answers automatically.
Automatic Prompt Generation via Adaptive Selection of Prompting Techniques
Computation and Language
Makes computers understand instructions better automatically.