PushGen: Push Notifications Generation with LLM
Abstract
We present PushGen, an automated framework for generating high-quality push notifications comparable to human-crafted content. With the rise of generative models, there is growing interest in leveraging LLMs for push content generation. Although LLMs make content generation straightforward and cost-effective, maintaining stylistic control and reliable quality assessment remains challenging, as both directly impact user engagement. To address these issues, PushGen combines two key components: (1) a controllable category prompt technique to guide LLM outputs toward desired styles, and (2) a reward model that ranks and selects generated candidates. Extensive offline and online experiments demonstrate its effectiveness, which has been deployed in large-scale industrial applications, serving hundreds of millions of users daily.
Fields of Study & Subjects
Advanced Text Analysis Techniques
Topic Modeling
Sentiment Analysis and Opinion Mining
Publication details
- Journal / source
- Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining
- Publisher
- ACM
- Pages
- 1073–1077
- Publication date
- 16 February 2026