LLM-Alignment Live-Streaming Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yueyang, Cao, Jiangxia, Wang, Shen, Wen, Shuang, Chen, Xiang, Wu, Xiangyu, Yang, Shuang, Liu, Zhaojie, Gai, Kun, Zhou, Guorui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910905478938624
author Liu, Yueyang
Cao, Jiangxia
Wang, Shen
Wen, Shuang
Chen, Xiang
Wu, Xiangyu
Yang, Shuang
Liu, Zhaojie
Gai, Kun
Zhou, Guorui
author_facet Liu, Yueyang
Cao, Jiangxia
Wang, Shen
Wen, Shuang
Chen, Xiang
Wu, Xiangyu
Yang, Shuang
Liu, Zhaojie
Gai, Kun
Zhou, Guorui
contents In recent years, integrated short-video and live-streaming platforms have gained massive global adoption, offering dynamic content creation and consumption. Unlike pre-recorded short videos, live-streaming enables real-time interaction between authors and users, fostering deeper engagement. However, this dynamic nature introduces a critical challenge for recommendation systems (RecSys): the same live-streaming vastly different experiences depending on when a user watching. To optimize recommendations, a RecSys must accurately interpret the real-time semantics of live content and align them with user preferences.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05217
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Alignment Live-Streaming Recommendation
Liu, Yueyang
Cao, Jiangxia
Wang, Shen
Wen, Shuang
Chen, Xiang
Wu, Xiangyu
Yang, Shuang
Liu, Zhaojie
Gai, Kun
Zhou, Guorui
Information Retrieval
In recent years, integrated short-video and live-streaming platforms have gained massive global adoption, offering dynamic content creation and consumption. Unlike pre-recorded short videos, live-streaming enables real-time interaction between authors and users, fostering deeper engagement. However, this dynamic nature introduces a critical challenge for recommendation systems (RecSys): the same live-streaming vastly different experiences depending on when a user watching. To optimize recommendations, a RecSys must accurately interpret the real-time semantics of live content and align them with user preferences.
title LLM-Alignment Live-Streaming Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2504.05217