用AI重写广告语，让广告更容易被搜索系统选中。
Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting
- 用强化学习优化广告文本，兼顾语义准确和原意保留。
- 在指令提示下提升广告入选率2.79倍，排序提升0.0073。
- 适合想提升广告曝光的数字营销与LLM应用开发者。
搜索引擎算法与用户查询相关性已使大语言模型具备返回相关内容的能力，但广告表述对广告可见性的影响仍缺乏研究。本文探讨基于大模型的广告重写如何提升其在检索系统中的排名及生成式大模型回复中的出现频率，且不改变检索模型本身。提出一种监督微调框架，采用自定义损失函数平衡语义相关性与内容保真度。为评估效果，引入两个指标：DeltaMRR@K（排序提升）与DeltaDIR@K（包含频率提升）。实验表明，在基于指令和少样本提示场景下，经PPO训练的模型优于提示工程与监督微调，在指令提示下最高实现2.79的DeltaDIR@5和0.0073的DeltaMRR@5。结果凸显了广告撰写前的表述方式、提示格式及强化学习在大模型集成检索系统中的重要性。
原文摘要 · Abstract (English)
Search algorithms and user query relevance have given LLMs the ability to return relevant information, but the effect of content phrasing on ad visibility remains underexplored. We investigate how LLM-based rewriting of advertisements can improve their ranking in retrieval systems and inclusion in generated LLM responses, without modifying the retrieval model itself. We introduce a supervised fine-tuning framework with a custom loss balancing semantic relevance and content fidelity. To evaluate effectiveness, we propose two metrics: DeltaMRR@K (ranking improvement) and DeltaDIR@K (inclusion frequency improvement). Our approach presents a scalable method to optimize ad phrasing, enhancing visibility in retrieval-based LLM workflows. Experiments across both instruction-based and few-shot prompting demonstrate that PPO trained models outperform both prompt engineering and supervised fine-tuning in most cases, achieving up to a 2.79 DeltaDIR@5 and 0.0073 DeltaMRR@5 in instruction-based prompting. These results highlight the importance of how the ad is written before retrieval and prompt format and reinforcement learning in effective ad rewriting for LLM integrated retrieval 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。