Saved in:
Bibliographic Details
Main Authors: Yuan, Jiahao, Xu, Yike, Wen, Jinyong, Wang, Baokun, Gao, Ziyi, Lin, Xiaotong, Liu, Yun, Fu, Xing, Cheng, Yu, Liu, Yongchao, Wang, Weiqiang, Xie, Zhongle
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.14492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910024403517440
author Yuan, Jiahao
Xu, Yike
Wen, Jinyong
Wang, Baokun
Gao, Ziyi
Lin, Xiaotong
Liu, Yun
Fu, Xing
Cheng, Yu
Liu, Yongchao
Wang, Weiqiang
Xie, Zhongle
author_facet Yuan, Jiahao
Xu, Yike
Wen, Jinyong
Wang, Baokun
Gao, Ziyi
Lin, Xiaotong
Liu, Yun
Fu, Xing
Cheng, Yu
Liu, Yongchao
Wang, Weiqiang
Xie, Zhongle
contents Industrial-scale user representation learning requires balancing robust universality with acute task-sensitivity. However, existing paradigms primarily yield static, task-agnostic embeddings that struggle to reconcile the divergent requirements of downstream scenarios within unified vector spaces. Furthermore, heterogeneous multi-source data introduces inherent noise and modality conflicts, degrading representation. We propose Query-as-Anchor, a framework shifting user modeling from static encoding to dynamic, query-aware synthesis. To empower Large Language Models (LLMs) with deep user understanding, we first construct UserU, an industrial-scale pre-training dataset that aligns multi-modal behavioral sequences with user understanding semantics, and our Q-Anchor Embedding architecture integrates hierarchical coarse-to-fine encoders into dual-tower LLMs via joint contrastive-autoregressive optimization for query-aware user representation. To bridge the gap between general pre-training and specialized business logic, we further introduce Cluster-based Soft Prompt Tuning to enforce discriminative latent structures, effectively aligning model attention with scenario-specific modalities. For deployment, anchoring queries at sequence termini enables KV-cache-accelerated inference with negligible incremental latency. Evaluations on 10 Alipay industrial benchmarks show consistent SOTA performance, strong scalability, and efficient deployment. Large-scale online A/B testing in Alipay's production system across two real-world scenarios further validates its practical effectiveness. Our code is prepared for public release and will be available at: https://github.com/JhCircle/Q-Anchor.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
Yuan, Jiahao
Xu, Yike
Wen, Jinyong
Wang, Baokun
Gao, Ziyi
Lin, Xiaotong
Liu, Yun
Fu, Xing
Cheng, Yu
Liu, Yongchao
Wang, Weiqiang
Xie, Zhongle
Computation and Language
Information Retrieval
Industrial-scale user representation learning requires balancing robust universality with acute task-sensitivity. However, existing paradigms primarily yield static, task-agnostic embeddings that struggle to reconcile the divergent requirements of downstream scenarios within unified vector spaces. Furthermore, heterogeneous multi-source data introduces inherent noise and modality conflicts, degrading representation. We propose Query-as-Anchor, a framework shifting user modeling from static encoding to dynamic, query-aware synthesis. To empower Large Language Models (LLMs) with deep user understanding, we first construct UserU, an industrial-scale pre-training dataset that aligns multi-modal behavioral sequences with user understanding semantics, and our Q-Anchor Embedding architecture integrates hierarchical coarse-to-fine encoders into dual-tower LLMs via joint contrastive-autoregressive optimization for query-aware user representation. To bridge the gap between general pre-training and specialized business logic, we further introduce Cluster-based Soft Prompt Tuning to enforce discriminative latent structures, effectively aligning model attention with scenario-specific modalities. For deployment, anchoring queries at sequence termini enables KV-cache-accelerated inference with negligible incremental latency. Evaluations on 10 Alipay industrial benchmarks show consistent SOTA performance, strong scalability, and efficient deployment. Large-scale online A/B testing in Alipay's production system across two real-world scenarios further validates its practical effectiveness. Our code is prepared for public release and will be available at: https://github.com/JhCircle/Q-Anchor.
title Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2602.14492