QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Tian, Zhang, Jiaqi, Liu, Yueyang, Dou, Hongjian, Yin, Tingya, Cao, Jiangxia, Liang, Xulei, Xie, Tianlu, Liu, Lihao, Chen, Xiang, Wang, Shen, Lao, Changxin, Gan, Haixiang, Yu, Jinkai, Cen, Keting, Hao, Lu, Zhang, Xu, Zhong, Qiqiang, Sun, Zhongbo, Wang, Yiyu, Yang, Shuang, Wen, Mingxin, Wu, Xiangyu, Liu, Shaoguo, Gao, Tingting, Liu, Zhaojie, Li, Han, Gai, Kun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911434379624448
author Xia, Tian
Zhang, Jiaqi
Liu, Yueyang
Dou, Hongjian
Yin, Tingya
Cao, Jiangxia
Liang, Xulei
Xie, Tianlu
Liu, Lihao
Chen, Xiang
Wang, Shen
Lao, Changxin
Gan, Haixiang
Yu, Jinkai
Cen, Keting
Hao, Lu
Zhang, Xu
Zhong, Qiqiang
Sun, Zhongbo
Wang, Yiyu
Yang, Shuang
Wen, Mingxin
Wu, Xiangyu
Liu, Shaoguo
Gao, Tingting
Liu, Zhaojie
Li, Han
Gai, Kun
author_facet Xia, Tian
Zhang, Jiaqi
Liu, Yueyang
Dou, Hongjian
Yin, Tingya
Cao, Jiangxia
Liang, Xulei
Xie, Tianlu
Liu, Lihao
Chen, Xiang
Wang, Shen
Lao, Changxin
Gan, Haixiang
Yu, Jinkai
Cen, Keting
Hao, Lu
Zhang, Xu
Zhong, Qiqiang
Sun, Zhongbo
Wang, Yiyu
Yang, Shuang
Wen, Mingxin
Wu, Xiangyu
Liu, Shaoguo
Gao, Tingting
Liu, Zhaojie
Li, Han
Gai, Kun
contents With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and weak generalization ability. While LLMs offer complementary strengths with dense semantic representations and strong generalization, directly applying LLM embeddings to RecSys faces critical challenges: representation unmatch with business objectives and representation unlearning end-to-end with downstream tasks. In this paper, we present QARM V2, a unified framework that bridges LLM semantic understanding with RecSys business requirements for user sequence modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08559
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling
Xia, Tian
Zhang, Jiaqi
Liu, Yueyang
Dou, Hongjian
Yin, Tingya
Cao, Jiangxia
Liang, Xulei
Xie, Tianlu
Liu, Lihao
Chen, Xiang
Wang, Shen
Lao, Changxin
Gan, Haixiang
Yu, Jinkai
Cen, Keting
Hao, Lu
Zhang, Xu
Zhong, Qiqiang
Sun, Zhongbo
Wang, Yiyu
Yang, Shuang
Wen, Mingxin
Wu, Xiangyu
Liu, Shaoguo
Gao, Tingting
Liu, Zhaojie
Li, Han
Gai, Kun
Information Retrieval
With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and weak generalization ability. While LLMs offer complementary strengths with dense semantic representations and strong generalization, directly applying LLM embeddings to RecSys faces critical challenges: representation unmatch with business objectives and representation unlearning end-to-end with downstream tasks. In this paper, we present QARM V2, a unified framework that bridges LLM semantic understanding with RecSys business requirements for user sequence modeling.
title QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling
topic Information Retrieval
url https://arxiv.org/abs/2602.08559