# RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation

arXiv: https://arxiv.org/abs/2602.11780 · HTML: https://mlsanity.com/paper/2602.11780/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 13 of 13)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model](https://mlsanity.com/paper/2306.02531/) (2023)
- [Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning](https://mlsanity.com/paper/2504.15275/) (2025)
- [CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment](https://mlsanity.com/paper/2508.02298/) (2025)
- [CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning](https://mlsanity.com/paper/2205.08943/) (2022)
- [Natural Language Generation for Advertising: A Survey](https://mlsanity.com/paper/2306.12719/) (2023)
- [CTR-Driven Ad Text Generation via Online Feedback Preference Optimization](https://mlsanity.com/paper/2507.20227/) (2025)
- [AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising](https://mlsanity.com/paper/2408.05906/) (2024)
- [LLM-driven Constrained Copy Generation through Iterative Refinement](https://mlsanity.com/paper/2504.10391/) (2025)

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

- [AgenticGen: Reward-Guided Agentic Video Generation for Advertising](https://mlsanity.com/paper/2609.09187/) (2026)
- [Marrying Pricing and Advertising with LLMs](https://mlsanity.com/paper/2610.09985/) (2026)

## Abstract (arXiv)

In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value. Existing industrial systems typically follow a two-stage paradigm, where candidate texts are first generated and subsequently aligned with online performance metrics such as click-through rate(CTR). This separation often leads to misaligned optimization objectives and low funnel efficiency, limiting global optimality. To address these limitations, we propose RELATE, a reinforcement learning-based end-to-end framework that unifies generation and objective alignment within a single model. Instead of decoupling text generation from downstream metric alignment, RELATE integrates performance and compliance objectives directly into the generation process via policy learning. To better capture ultimate advertiser value beyond click-level signals, We incorporate conversion-oriented metrics into the objective and jointly model them with compliance constraints as multi-dimensional rewards, enabling the model to generate high-quality ad texts that improve conversion performance under policy constraints. Extensive experiments on large-scale industrial datasets demonstrate that RELATE consistently outperforms baselines. Furthermore, online deployment on a production advertising platform yields statistically significant improvements in click-through conversion rate(CTCVR) under strict policy constraints, validating the robustness and real-world effectiveness of the proposed framework.