PushGen: Push Notifications Generation with LLM
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Intelligent Notification Composition | PushGen Social Media | CTR14.08 | 1 | |
| Push Notification Generation | Push service (Overall User) | DAU (Dedup.)6.7 | 1 | |
| Push Notification Generation | Push service (Mid Active User) | DAU Change (Dedup.)0.196 | 1 | |
| Push Notification Generation | Push service (Low Active User) | DAU (Dedup.)0.176 | 1 |