arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.09862cs.NEcs.AIcs.CLcs.LG
收藏

用于平衡情感的大语言模型提示的进化多目标优化

Evolutionary Multi-Objective Optimization of Large Language Model Prompts for Balancing Sentiments

Carl von Ossietzky Universität Oldenburg(奥尔登堡卡尔·冯·奥西茨基大学)

Jill Baumann, Oliver Kramer

AI总结:

本文提出 EMO-Prompts,利用进化多目标优化自动生成提示,并以情感分析验证其可引导大语言模型同时表达两种冲突情感。

摘要:

诸如 ChatGPT 之类的大语言模型(LLM)的出现,凭借其卓越性能和多功能性,在各个领域引起了广泛关注。随着这些模型的使用持续增长,有效提示工程的重要性凸显出来。提示优化成为一项关键挑战,因为它直接影响模型性能和相关信息的提取。近来,进化算法(EA)在解决该问题方面展现出前景,为新型优化策略铺平了道路。在本研究中,我们提出一种专为提示优化定制的进化多目标(EMO)方法,名为 EMO-Prompts,并以情感分析作为案例研究。我们将情感分析能力作为实验目标。结果表明,EMO-Prompts 能够有效生成提示,引导 LLM 产出同时体现两种相互冲突情感的文本。

英文摘要:

The advent of large language models (LLMs) such as ChatGPT has attracted considerable attention in various domains due to their remarkable performance and versatility. As the use of these models continues to grow, the importance of effective prompt engineering has come to the fore. Prompt optimization emerges as a crucial challenge, as it has a direct impact on model performance and the extraction of relevant information. Recently, evolutionary algorithms (EAs) have shown promise in addressing this issue, paving the way for novel optimization strategies. In this work, we propose a evolutionary multi-objective (EMO) approach specifically tailored for prompt optimization called EMO-Prompts, using sentiment analysis as a case study. We use sentiment analysis capabilities as our experimental targets. Our results demonstrate that EMO-Prompts effectively generates prompts capable of guiding the LLM to produce texts embodying two conflicting emotions simultaneously.

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。

↑