用在线点击反馈优化广告文案，提升点击率
CTR-Driven Ad Text Generation via Online Feedback Preference Optimization
- 两阶段生成：先用检索增强生成多样文案，再根据点击收益优化偏好
- 在线反馈加权偏好对，点击率提升显著，实测效果优于人工文案
- 适合广告系统研发者，尤其关注点击转化的场景
广告文案直接影响在线广告的点击率（CTR）。大语言模型（LLMs）在生成效率上远超人工撰写，但其生成的文案未必比人工文案带来更高点击率，暴露出生成质量与实际表现之间的差距。本文提出一种基于在线反馈偏好的点击率驱动广告文案生成方法。该方法采用创新的两阶段框架：（1）通过单次上下文学习采样多样文案，结合检索增强生成（RAG）提供带思维链（CoT）推理的示例；（2）基于在线反馈进行点击率驱动的偏好优化，根据点击收益和置信度对偏好对进行加权。所提方法实现高点击率广告文案的端到端生成。大量实验表明，该方法在离线与在线指标上均有效。尤其在大规模电商平台上的应用中，显著提升了点击率，验证了其在广告系统中的强适用性与有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。