Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting
This addresses the underexplored effect of content phrasing on ad visibility for advertisers in LLM-integrated retrieval systems, presenting a scalable incremental method.
The paper tackles the problem of improving ad visibility in retrieval-based LLM systems by optimizing ad phrasing through LLM-based rewriting, achieving up to a 2.79 DeltaDIR@5 and 0.0073 DeltaMRR@5 in experiments.
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.