{"ID":2889914,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20227","arxiv_id":"2507.20227","title":"CTR-Driven Ad Text Generation via Online Feedback Preference Optimization","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.","short_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 g...","url_abs":"https://arxiv.org/abs/2507.20227","url_pdf":"https://arxiv.org/pdf/2507.20227v3","authors":"[\"Yanda Chen\",\"Zihui Ren\",\"Qixiang Gao\",\"Jiale Chen\",\"Si Chen\",\"Xubin Li\",\"Tiezheng Ge\",\"Bo Zheng\"]","published":"2025-07-27T11:13:03Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}