CTR-Driven Ad Text Generation via Online Feedback Preference Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yanda, Ren, Zihui, Gao, Qixiang, Chen, Jiale, Chen, Si, Li, Xubin, Ge, Tiezheng, Zheng, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912515576823808
author Chen, Yanda
Ren, Zihui
Gao, Qixiang
Chen, Jiale
Chen, Si
Li, Xubin
Ge, Tiezheng
Zheng, Bo
author_facet Chen, Yanda
Ren, Zihui
Gao, Qixiang
Chen, Jiale
Chen, Si
Li, Xubin
Ge, Tiezheng
Zheng, Bo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20227
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CTR-Driven Ad Text Generation via Online Feedback Preference Optimization
Chen, Yanda
Ren, Zihui
Gao, Qixiang
Chen, Jiale
Chen, Si
Li, Xubin
Ge, Tiezheng
Zheng, Bo
Information Retrieval
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.
title CTR-Driven Ad Text Generation via Online Feedback Preference Optimization
topic Information Retrieval
url https://arxiv.org/abs/2507.20227