arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.01260cs.CLcs.AI
收藏

SPELL:基于大语言模型的语义提示词进化

SPELL: Semantic Prompt Evolution based on a LLM

School of Artificial Intelligence, Xidian University(西安电子科技大学人工智能学院);Institute of Freedom and Happiness(自由幸福研究院)

Yujian Betterest Li, Kai Wu

AI总结:

针对现有文本提示词优化方法易破坏流畅性或无法全局调整的问题,提出基于大语言模型的黑盒进化算法SPELL,实验验证其可快速优化提示词,并探讨了局限与未来方向。

摘要:

提示工程是提升已训练神经网络模型性能的新范式。针对文本类提示词的优化,现有方法通常逐步对文本的局部进行单独修改,这要么会破坏流畅性,要么无法对提示词进行全局调整。鉴于大语言模型(LLMs)具备逐token生成连贯文本的强大能力,我们能否利用LLM来优化提示词?基于这一动机,本文将已训练的LLM视作文本生成器,尝试设计一种黑盒进化算法以自动优化文本,即SPELL(基于LLM的语义提示词进化)。我们在不同文本任务中,采用不同LLM和进化参数对所提方法进行了评估。实验结果表明,SPELL确实能够快速优化提示词。我们进一步探究了进化过程,并讨论了该方法的局限性、潜在可能性与未来工作方向。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑