用大模型自动生成高质量推送通知，效果媲美人工
PushGen: Push Notifications Generation with LLM
- 通过可控提示词引导大模型输出指定风格内容
- 采用评分模型筛选优质候选，保证生成质量
- 已在大规模工业场景落地，日均服务数亿用户
我们提出PushGen，一个自动化生成高质量推送通知的框架，其效果可媲美人工撰写。随着生成模型的发展，利用大语言模型（LLM）生成推送内容愈发流行。尽管LLM使内容生成变得简单且低成本，但保持风格控制和可靠的质量评估仍具挑战，而这两点直接影响用户参与度。为解决此问题，PushGen结合两项关键技术：(1) 可控类别提示词技术，用于引导LLM输出符合特定风格的内容；(2) 奖励模型，用于对生成结果进行排序与优选。大量离线与在线实验验证了其有效性，该系统已部署于大规模工业应用中，每日服务数亿用户。
原文摘要 · Abstract (English)
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.
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。