# CTR-Driven Ad Text Generation via Online Feedback Preference Optimization

arXiv: https://arxiv.org/abs/2507.20227 · HTML: https://mlsanity.com/paper/2507.20227/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2025.

## Built on by (most cited first, 8 of 8)

- [RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation](https://mlsanity.com/paper/2602.11780/) (2026)
- [Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models](https://mlsanity.com/paper/2605.12138/) (2026)
- [Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search](https://mlsanity.com/paper/2606.15911/) (2026)
- [AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions](https://mlsanity.com/paper/2509.11151/) (2025)
- [Recontextualizing Famous Quotes for Brand Slogan Generation](https://mlsanity.com/paper/2602.06049/) (2026)
- [AgenticGen: Reward-Guided Agentic Video Generation for Advertising](https://mlsanity.com/paper/2609.09187/) (2026)
- [How Can Recommendation Feedback Evolve Agent Memory?](https://mlsanity.com/paper/2609.37544/) (2026)
- [Marrying Pricing and Advertising with LLMs](https://mlsanity.com/paper/2610.09985/) (2026)

## Abstract (arXiv)

Advertising text plays a critical role in determining click-through rates (CTR) in online advertising. Large Language Models (LLMs) offer significant efficiency advantages over manual ad text creation. However, LLM-generated ad texts do not guarantee higher CTR performance compared to human-crafted texts, revealing a gap between generation quality and online performance of ad texts. In this work, we propose a novel ad text generation method which optimizes for CTR through preference optimization from online feedback. Our approach adopts an innovative two-stage framework: (1) diverse ad text sampling via one-shot in-context learning, using retrieval-augmented generation (RAG) to provide exemplars with chain-of-thought (CoT) reasoning; (2) CTR-driven preference optimization from online feedback, which weighs preference pairs according to their CTR gains and confidence levels. Through our method, the resulting model enables end-to-end generation of high-CTR ad texts. Extensive experiments have demonstrated the effectiveness of our method in both offline and online metrics. Notably, we have applied our method on a large-scale online shopping platform and achieved significant CTR improvements, showcasing its strong applicability and effectiveness in advertising systems.