用分层大模型实现广告内容个性化生成，提升用户点击率。
HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
- 分层架构结合用户聚类与匹配预测，高效建模用户兴趣。
- 在抖音搜索广告上实现0.476%的点击率提升，实测有效。
- 自动生成高质量标题，适合工业级大规模个性化内容场景。
AI生成内容技术广泛应用于内容创作，但现有AIGC系统高度依赖创作者灵感，难以生成真正用户个性化的内容。在在线广告等实际场景中，同一产品有多个卖点，不同用户关注点各异，凸显个性化、以用户为中心的内容生成价值。有效实现个性化生成面临两大挑战：一是准确建模用户兴趣并融入生成过程，同时遵守事实约束；二是确保高效率与可扩展性，以应对工业级海量用户。此外，真实场景中个性化创意数据稀缺，制约模型训练，数据构建成为关键难题。本文提出HLLM-Creator，一种基于分层大模型的高效用户兴趣建模与个性化内容生成框架。推理阶段采用用户聚类与基于用户-广告匹配预测的剪枝策略，显著提升生成效率并降低计算开销，适用于大规模部署。我们设计了一套基于思维链推理的数据构建管道，生成高质量、用户特定的创意标题，并保证事实一致性，即使在个性化数据有限的情况下。该管道为模型有效性提供关键支撑。在抖音搜索广告个性化标题生成任务上的大量实验验证了HLLM-Creator的有效性。线上A/B测试显示广告点击率提升0.476%，为工业场景下的高效个性化生成提供了可行路径。学术数据集代码已开源：https://github.com/bytedance/HLLM。
原文摘要 · Abstract (English)
AI-generated content technologies are widely used in content creation. However, current AIGC systems rely heavily on creators' inspiration, rarely generating truly user-personalized content. In real-world applications such as online advertising, a single product may have multiple selling points, with different users focusing on different features. This underscores the significant value of personalized, user-centric creative generation. Effective personalized content generation faces two main challenges: (1) accurately modeling user interests and integrating them into the content generation process while adhering to factual constraints, and (2) ensuring high efficiency and scalability to handle the massive user base in industrial scenarios. Additionally, the scarcity of personalized creative data in practice complicates model training, making data construction another key hurdle. We propose HLLM-Creator, a hierarchical LLM framework for efficient user interest modeling and personalized content generation. During inference, a combination of user clustering and a user-ad-matching-prediction based pruning strategy is employed to significantly enhance generation efficiency and reduce computational overhead, making the approach suitable for large-scale deployment. Moreover, we design a data construction pipeline based on chain-of-thought reasoning, which generates high-quality, user-specific creative titles and ensures factual consistency despite limited personalized data. This pipeline serves as a critical foundation for the effectiveness of our model. Extensive experiments on personalized title generation for Douyin Search Ads show the effectiveness of HLLM-Creator. Online A/B test shows a 0.476% increase on Adss, paving the way for more effective and efficient personalized generation in industrial scenarios. Codes for academic dataset are available at https://github.com/bytedance/HLLM.
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。