GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910019622010880 |
|---|---|
| author | Zhang, Jun Li, Yi Liu, Yue Wang, Changping Wang, Yuan Xiong, Yuling Liu, Xun Wu, Haiyang Li, Qian Zhang, Enming Sun, Jiawei Xu, Xin Zhang, Zishuai Liu, Ruoran Huang, Suyuan Zhang, Zhaoxin Guo, Zhengkai Yang, Shuojin Guo, Meng-Hao Yu, Huan Jiang, Jie Hu, Shi-Min |
| author_facet | Zhang, Jun Li, Yi Liu, Yue Wang, Changping Wang, Yuan Xiong, Yuling Liu, Xun Wu, Haiyang Li, Qian Zhang, Enming Sun, Jiawei Xu, Xin Zhang, Zishuai Liu, Ruoran Huang, Suyuan Zhang, Zhaoxin Guo, Zhengkai Yang, Shuojin Guo, Meng-Hao Yu, Huan Jiang, Jie Hu, Shi-Min |
| contents | As an intelligent infrastructure connecting users with commercial content, advertising recommendation systems play a central role in information flow and value creation within the digital economy. However, existing multi-stage advertising recommendation systems suffer from objective misalignment and error propagation, making it difficult to achieve global optimality, while unified generative recommendation models still struggle to meet the demands of practical industrial applications. To address these issues, we propose GPR (Generative Pre-trained Recommender), the first one-model framework that redefines advertising recommendation as an end-to-end generative task, replacing the traditional cascading paradigm with a unified generative approach. To realize GPR, we introduce three key innovations spanning unified representation, network architecture, and training strategy. First, we design a unified input schema and tokenization method tailored to advertising scenarios, mapping both ads and organic content into a shared multi-level semantic ID space, thereby enhancing semantic alignment and modeling consistency across heterogeneous data. Second, we develop the Heterogeneous Hierarchical Decoder (HHD), a dual-decoder architecture that decouples user intent modeling from ad generation, achieving a balance between training efficiency and inference flexibility while maintaining strong modeling capacity. Finally, we propose a multi-stage joint training strategy that integrates Multi-Token Prediction (MTP), Value-Aware Fine-Tuning and the Hierarchy Enhanced Policy Optimization (HEPO) algorithm, forming a complete generative recommendation pipeline that unifies interest modeling, value alignment, and policy optimization. GPR has been fully deployed in the Tencent Weixin Channels advertising system, delivering significant improvements in key business metrics including GMV and CTCVR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10138 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation Zhang, Jun Li, Yi Liu, Yue Wang, Changping Wang, Yuan Xiong, Yuling Liu, Xun Wu, Haiyang Li, Qian Zhang, Enming Sun, Jiawei Xu, Xin Zhang, Zishuai Liu, Ruoran Huang, Suyuan Zhang, Zhaoxin Guo, Zhengkai Yang, Shuojin Guo, Meng-Hao Yu, Huan Jiang, Jie Hu, Shi-Min Information Retrieval As an intelligent infrastructure connecting users with commercial content, advertising recommendation systems play a central role in information flow and value creation within the digital economy. However, existing multi-stage advertising recommendation systems suffer from objective misalignment and error propagation, making it difficult to achieve global optimality, while unified generative recommendation models still struggle to meet the demands of practical industrial applications. To address these issues, we propose GPR (Generative Pre-trained Recommender), the first one-model framework that redefines advertising recommendation as an end-to-end generative task, replacing the traditional cascading paradigm with a unified generative approach. To realize GPR, we introduce three key innovations spanning unified representation, network architecture, and training strategy. First, we design a unified input schema and tokenization method tailored to advertising scenarios, mapping both ads and organic content into a shared multi-level semantic ID space, thereby enhancing semantic alignment and modeling consistency across heterogeneous data. Second, we develop the Heterogeneous Hierarchical Decoder (HHD), a dual-decoder architecture that decouples user intent modeling from ad generation, achieving a balance between training efficiency and inference flexibility while maintaining strong modeling capacity. Finally, we propose a multi-stage joint training strategy that integrates Multi-Token Prediction (MTP), Value-Aware Fine-Tuning and the Hierarchy Enhanced Policy Optimization (HEPO) algorithm, forming a complete generative recommendation pipeline that unifies interest modeling, value alignment, and policy optimization. GPR has been fully deployed in the Tencent Weixin Channels advertising system, delivering significant improvements in key business metrics including GMV and CTCVR. |
| title | GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2511.10138 |