PushGen: Push Notifications Generation with LLM

TL;DR

PushGen is an innovative framework that leverages large language models with controllable prompts and reward-based ranking to generate high-quality, style-controlled push notifications at scale, enhancing user engagement.

Contribution

It introduces a novel combination of controllable prompts and reward models for high-quality push notification generation using LLMs, deployed at industrial scale.

Findings

Effective in generating high-quality notifications

Successfully deployed for hundreds of millions of users

Outperforms baseline methods in quality and engagement

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.