{"ID":2877949,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.18739","arxiv_id":"2508.18739","title":"Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models","abstract":"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%.","short_abstract":"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 resu...","url_abs":"https://arxiv.org/abs/2508.18739","url_pdf":"https://arxiv.org/pdf/2508.18739v1","authors":"[\"Chang Wang\",\"Siyu Yan\",\"Depeng Yuan\",\"Yuqi Chen\",\"Yanhua Huang\",\"Yuanhang Zheng\",\"Shuhao Li\",\"Yinqi Zhang\",\"Kedi Chen\",\"Mingrui Zhu\",\"Ruiwen Xu\"]","published":"2025-08-26T07:11:44Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}