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 2402.13667cs.CL
收藏

GCOF:基于大语言模型的自我迭代文案生成方法

GCOF: Self-iterative Text Generation for Copywriting Using Large Language Model

JingDong Technology(京东科技)

Jianghui Zhou, Ya Gao, Jie Liu, Xuemin Zhao, Zhaohua Yang, Yue Wu, Lirong Shi

AI总结:

本文提出 GCOF 框架,通过改进遗传算法交叉算子并结合大语言模型提示词特征工程,实现营销文案的自我迭代优化,使点击率平均提升超过 50%。

摘要:

ChatGPT 等大语言模型(LLM)已大幅简化了营销文案的生成,但产出满足特定领域要求(如有效吸引客户)的内容仍是一项重大挑战。在本工作中,我们提出了遗传文案优化框架(Genetic Copy Optimization Framework,GCOF),旨在提升营销文案创作的效率和吸引力。我们在 LLM 的提示词中进行显式特征工程。此外,我们改进了遗传算法(Genetic Algorithm,GA)中的交叉算子,并将其集成到 GCOF 中,以实现自动特征工程。这一集成促进了营销文案的自我迭代优化。与人工策划的文案相比,在线结果表明,我们的框架所生成的文案在点击率(CTR)上平均提升了超过 50%。

英文摘要:

Large language models(LLM) such as ChatGPT have substantially simplified the generation of marketing copy, yet producing content satisfying domain specific requirements, such as effectively engaging customers, remains a significant challenge. In this work, we introduce the Genetic Copy Optimization Framework (GCOF) designed to enhance both efficiency and engagememnt of marketing copy creation. We conduct explicit feature engineering within the prompts of LLM. Additionally, we modify the crossover operator in Genetic Algorithm (GA), integrating it into the GCOF to enable automatic feature engineering. This integration facilitates a self-iterative refinement of the marketing copy. Compared to human curated copy, Online results indicate that copy produced by our framework achieves an average increase in click-through rate (CTR) of over $50\%$.

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。

↑