SPELL: Semantic Prompt Evolution based on a LLM
This work addresses prompt engineering for LLM users, presenting an incremental improvement over existing methods by enabling global adjustments without breaking fluency.
The paper tackles the problem of optimizing text prompts for large language models (LLMs) by proposing SPELL, a black-box evolution algorithm that automatically improves prompts, with experimental results showing rapid enhancement in performance.
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.