用大模型同时提升广告标题质量和多样性，效果更优。
Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models
- 设计新数据生成流程，自动产出高质量多样标题对。
- 单次推理即可生成高质且多样的广告标题，提升点击率1.4%。
- 适合需要覆盖广泛受众的广告平台和内容创作者。
广告标题生成在现代广告中至关重要，质量与多样性均需兼顾以触达多元用户群体。现有方法主要优化标题质量或点击率（CTR），常忽视多样性，导致输出同质化。为此，我们提出DIVER框架，基于大语言模型（LLMs）联合优化质量与多样性。首先设计一种语义与风格感知的数据生成流程，自动构建高质量训练样本对（广告内容与多个多样化标题）。为实现单次前向传播生成高质量、多样化的标题，提出多阶段多目标优化框架，结合监督微调（SFT）与强化学习（RL）。在真实工业数据集上的实验表明，DIVER能有效平衡质量与多样性。部署于服务数亿用户的大型内容分享平台后，广告主价值（ADVV）和CTR分别提升4.0%和1.4%。
原文摘要 · Abstract (English)
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%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。