SPELL: Semantic Prompt Evolution based on a LLM

TL;DR

This paper introduces SPELL, a black-box evolution algorithm leveraging large language models to automatically optimize text prompts, improving their quality efficiently across various tasks.

Contribution

It presents a novel method that uses LLMs for prompt evolution, addressing limitations of existing prompt engineering techniques.

Findings

SPELL rapidly improves prompt quality in experiments

The method is effective across different LLMs and tasks

Discussion on limitations and future directions included

Abstract

Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks the fluency or could not globally adjust a prompt. Since large language models (LLMs) have powerful ability of generating coherent texts token by token, can we utilize LLMs for improving prompts? Based on this motivation, in this paper, considering a trained LLM as a text generator, we attempt to design a black-box evolution algorithm for automatically optimizing texts, namely SPELL (Semantic Prompt Evolution based on a LLM). The proposed method is evaluated with different LLMs and evolution parameters in different text tasks. Experimental results show that SPELL could rapidly improve the prompts indeed. We further explore the evolution process and discuss on the limitations, potential possibilities and future work.