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

arXiv: https://arxiv.org/abs/2402.13667 · HTML: https://mlsanity.com/paper/2402.13667/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 21 of 21)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [GSum: A General Framework for Guided Neural Abstractive Summarization](https://mlsanity.com/paper/2010.08014/) (2020)
- [Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction](https://mlsanity.com/paper/1905.09248/) (2019)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [Controlled Text Generation via Language Model Arithmetic](https://mlsanity.com/paper/2311.14479/) (2023)
- [StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer](https://mlsanity.com/paper/2104.05196/) (2021)
- [Click-Through Rate Prediction in Online Advertising: A Literature Review](https://mlsanity.com/paper/2202.10462/) (2022)
- [MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction](https://mlsanity.com/paper/2008.02974/) (2020)
- [CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning](https://mlsanity.com/paper/2205.08943/) (2022)
- [A Survey on Large Language Models for Personalized and Explainable Recommendations](https://mlsanity.com/paper/2311.12338/) (2023)
- [TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity](https://mlsanity.com/paper/2108.08226/) (2021)
- [IA-GCN: Interactive Graph Convolutional Network for Recommendation](https://mlsanity.com/paper/2204.03827/) (2022)

## Abstract (arXiv)

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%.