PushGen: Push Notifications Generation with LLM

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bie, Shifu, Cao, Jiangxia, Luo, Zixiao, Zou, Yichuan, Liang, Lei, Zhang, Lu, Chen, Linxun, Liu, Zhaojie, Li, Xuanping, Zhou, Guorui, Zhan, Kaiqiao, Gai, Kun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912768662175744
author Bie, Shifu
Cao, Jiangxia
Luo, Zixiao
Zou, Yichuan
Liang, Lei
Zhang, Lu
Chen, Linxun
Liu, Zhaojie
Li, Xuanping
Zhou, Guorui
Zhan, Kaiqiao
Gai, Kun
author_facet Bie, Shifu
Cao, Jiangxia
Luo, Zixiao
Zou, Yichuan
Liang, Lei
Zhang, Lu
Chen, Linxun
Liu, Zhaojie
Li, Xuanping
Zhou, Guorui
Zhan, Kaiqiao
Gai, Kun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14490
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PushGen: Push Notifications Generation with LLM
Bie, Shifu
Cao, Jiangxia
Luo, Zixiao
Zou, Yichuan
Liang, Lei
Zhang, Lu
Chen, Linxun
Liu, Zhaojie
Li, Xuanping
Zhou, Guorui
Zhan, Kaiqiao
Gai, Kun
Information Retrieval
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.
title PushGen: Push Notifications Generation with LLM
topic Information Retrieval
url https://arxiv.org/abs/2512.14490