# LLM-driven Constrained Copy Generation through Iterative Refinement

arXiv: https://arxiv.org/abs/2504.10391 · HTML: https://mlsanity.com/paper/2504.10391/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 19 of 19)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [The Next Chapter: A Study of Large Language Models in Storytelling](https://mlsanity.com/paper/2301.09790/) (2023)
- [A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion Model](https://mlsanity.com/paper/2401.10934/) (2024)
- [Weaver: Foundation Models for Creative Writing](https://mlsanity.com/paper/2401.17268/) (2024)
- [CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning](https://mlsanity.com/paper/2205.08943/) (2022)
- [Chaining text-to-image and large language model: A novel approach for generating personalized e-commerce banners](https://mlsanity.com/paper/2403.05578/) (2024)
- [Controllable Text Generation in the Instruction-Tuning Era](https://mlsanity.com/paper/2405.01490/) (2024)
- [Automatic Controllable Product Copywriting for E-Commerce](https://mlsanity.com/paper/2206.10103/) (2022)
- [Improved Diversity Maximization Algorithms for Matching and Pseudoforest](https://mlsanity.com/paper/2307.04329/) (2023)
- [Generating Attractive and Authentic Copywriting from Customer Reviews](https://mlsanity.com/paper/2404.13906/) (2024)

## Built on by (most cited first, 3 of 3)

- [HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation](https://mlsanity.com/paper/2508.18118/) (2025)
- [RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation](https://mlsanity.com/paper/2602.11780/) (2026)
- [Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction](https://mlsanity.com/paper/2604.19971/) (2026)

## Abstract (arXiv)

Crafting a marketing message (copy), or copywriting is a challenging generation task, as the copy must adhere to various constraints. Copy creation is inherently iterative for humans, starting with an initial draft followed by successive refinements. However, manual copy creation is time-consuming and expensive, resulting in only a few copies for each use case. This limitation restricts our ability to personalize content to customers. Contrary to the manual approach, LLMs can generate copies quickly, but the generated content does not consistently meet all the constraints on the first attempt (similar to humans). While recent studies have shown promise in improving constrained generation through iterative refinement, they have primarily addressed tasks with only a few simple constraints. Consequently, the effectiveness of iterative refinement for tasks such as copy generation, which involves many intricate constraints, remains unclear. To address this gap, we propose an LLM-based end-to-end framework for scalable copy generation using iterative refinement. To the best of our knowledge, this is the first study to address multiple challenging constraints simultaneously in copy generation. Examples of these constraints include length, topics, keywords, preferred lexical ordering, and tone of voice. We demonstrate the performance of our framework by creating copies for e-commerce banners for three different use cases of varying complexity. Our results show that iterative refinement increases the copy success rate by 16.25-35.91% across use cases. Furthermore, the copies generated using our approach outperformed manually created content in multiple pilot studies using a multi-armed bandit framework. The winning copy improved the click-through rate by 38.5-45.21%.