CTR-Driven Ad Text Generation via Online Feedback Preference Optimization

TL;DR

This paper introduces a two-stage CTR-driven ad text generation framework that leverages online feedback and retrieval-augmented generation to produce high-CTR advertisements, outperforming traditional methods.

Contribution

It presents a novel two-stage approach combining diverse sampling with preference optimization from online feedback to enhance ad text CTR performance.

Findings

Significant CTR improvements in online shopping platform deployment

Effective offline and online performance demonstrated

Utilizes retrieval-augmented generation with chain-of-thought reasoning

Abstract

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.