{"ID":2828563,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.14490","arxiv_id":"2512.14490","title":"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.","short_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, maintaini...","url_abs":"https://arxiv.org/abs/2512.14490","url_pdf":"https://arxiv.org/pdf/2512.14490v1","authors":"[\"Shifu Bie\",\"Jiangxia Cao\",\"Zixiao Luo\",\"Yichuan Zou\",\"Lei Liang\",\"Lu Zhang\",\"Linxun Chen\",\"Zhaojie Liu\",\"Xuanping Li\",\"Guorui Zhou\",\"Kaiqiao Zhan\",\"Kun Gai\"]","published":"2025-12-16T15:23:28Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Large Language Model\"]","has_code":false}