Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912555053613056 |
|---|---|
| author | Wang, Chang Yan, Siyu Yuan, Depeng Chen, Yuqi Huang, Yanhua Zheng, Yuanhang Li, Shuhao Zhang, Yinqi Chen, Kedi Zhu, Mingrui Xu, Ruiwen |
| author_facet | Wang, Chang Yan, Siyu Yuan, Depeng Chen, Yuqi Huang, Yanhua Zheng, Yuanhang Li, Shuhao Zhang, Yinqi Chen, Kedi Zhu, Mingrui Xu, Ruiwen |
| contents | The generation of ad headlines plays a vital role in modern advertising, where both quality and diversity are essential to engage a broad range of audience segments. Current approaches primarily optimize language models for headline quality or click-through rates (CTR), often overlooking the need for diversity and resulting in homogeneous outputs. To address this limitation, we propose DIVER, a novel framework based on large language models (LLMs) that are jointly optimized for both diversity and quality. We first design a semantic- and stylistic-aware data generation pipeline that automatically produces high-quality training pairs with ad content and multiple diverse headlines. To achieve the goal of generating high-quality and diversified ad headlines within a single forward pass, we propose a multi-stage multi-objective optimization framework with supervised fine-tuning (SFT) and reinforcement learning (RL). Experiments on real-world industrial datasets demonstrate that DIVER effectively balances quality and diversity. Deployed on a large-scale content-sharing platform serving hundreds of millions of users, our framework improves advertiser value (ADVV) and CTR by 4.0% and 1.4%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18739 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models Wang, Chang Yan, Siyu Yuan, Depeng Chen, Yuqi Huang, Yanhua Zheng, Yuanhang Li, Shuhao Zhang, Yinqi Chen, Kedi Zhu, Mingrui Xu, Ruiwen Computation and Language Machine Learning The generation of ad headlines plays a vital role in modern advertising, where both quality and diversity are essential to engage a broad range of audience segments. Current approaches primarily optimize language models for headline quality or click-through rates (CTR), often overlooking the need for diversity and resulting in homogeneous outputs. To address this limitation, we propose DIVER, a novel framework based on large language models (LLMs) that are jointly optimized for both diversity and quality. We first design a semantic- and stylistic-aware data generation pipeline that automatically produces high-quality training pairs with ad content and multiple diverse headlines. To achieve the goal of generating high-quality and diversified ad headlines within a single forward pass, we propose a multi-stage multi-objective optimization framework with supervised fine-tuning (SFT) and reinforcement learning (RL). Experiments on real-world industrial datasets demonstrate that DIVER effectively balances quality and diversity. Deployed on a large-scale content-sharing platform serving hundreds of millions of users, our framework improves advertiser value (ADVV) and CTR by 4.0% and 1.4%. |
| title | Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2508.18739 |