# Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting

arXiv: https://arxiv.org/abs/2507.21099 · HTML: https://mlsanity.com/paper/2507.21099/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 3 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations](https://mlsanity.com/paper/2504.14150/) (2025)
- [What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary](https://mlsanity.com/paper/2212.10380/) (2022)
- [Expansion via Prediction of Importance with Contextualization](https://mlsanity.com/paper/2004.14245/) (2020)
- [Evaluating the Retrieval Component in LLM-Based Question Answering Systems](https://mlsanity.com/paper/2406.06458/) (2024)
- [Deep Ranking with Adaptive Margin Triplet Loss](https://mlsanity.com/paper/2107.06187/) (2021)
- [Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets](https://mlsanity.com/paper/2504.20119/) (2025)
- [Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering](https://mlsanity.com/paper/2212.10696/) (2022)
- [Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model](https://mlsanity.com/paper/2409.17745/) (2024)
- [Adaptive Weight Assignment Scheme For Multi-task Learning](https://mlsanity.com/paper/2303.07278/) (2023)
- [Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation](https://mlsanity.com/paper/2411.03957/) (2024)
- [Sponsored is the New Organic: Implications of Sponsored Results on Quality of Search Results in the Amazon Marketplace](https://mlsanity.com/paper/2407.19099/) (2024)

## Built on by (most cited first, 2 of 2)

- [GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization](https://mlsanity.com/paper/2605.29107/) (2026)
- [Exploring LLM biases to manipulate AI search overview](https://mlsanity.com/paper/2605.00012/) (2026)

## Abstract (arXiv)

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.