HiGR: Efficient Generative Slate Recommendation via Hierarchical Planning and Multi-Objective Preference Alignment

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pang, Yunsheng, Liu, Zijian, Li, Yudong, Zhu, Shaojie, Luo, Zijian, Yu, Chenyun, Wu, Sikai, Shen, Shichen, Xu, Cong, Wang, Bin, Jiang, Kai, Yu, Hongyong, Zhuo, Chengxiang, Li, Zang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910030930903040
author Pang, Yunsheng
Liu, Zijian
Li, Yudong
Zhu, Shaojie
Luo, Zijian
Yu, Chenyun
Wu, Sikai
Shen, Shichen
Xu, Cong
Wang, Bin
Jiang, Kai
Yu, Hongyong
Zhuo, Chengxiang
Li, Zang
author_facet Pang, Yunsheng
Liu, Zijian
Li, Yudong
Zhu, Shaojie
Luo, Zijian
Yu, Chenyun
Wu, Sikai
Shen, Shichen
Xu, Cong
Wang, Bin
Jiang, Kai
Yu, Hongyong
Zhuo, Chengxiang
Li, Zang
contents Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. Recent advances in generative models have shown significant potential for this task via autoregressive modeling of discrete semantic ID sequences. However, existing methods suffer from three key limitations: entangled item tokenization, inefficient sequential decoding, and the absence of holistic slate planning. These issues often result in substantial inference overhead and inadequate alignment with diverse user preferences and practical business requirements, hindering the industrial deployment of generative slate recommendation systems. In this paper, we propose HiGR, an efficient generative slate recommendation framework that integrates hierarchical planning with listwise preference alignment. First, we design an auto-encoder incorporating residual quantization and contrastive constraints, which tokenizes items into semantically structured IDs to enable controllable generation. Second, HiGR decouples the generation process into two stages: a list-level planning stage to capture global slate intent, and an item-level decoding stage to select specific items, effectively reducing the search space and enabling efficient generation. Third, we introduce a multi-objective and listwise preference alignment mechanism that enhances slate quality by leveraging implicit user feedback. Extensive experiments have validated the effectiveness of our HiGR method. Notably, it outperforms state-of-the-art baselines by over 10\% in offline recommendation quality while achieving a $5\times$ inference speedup. Furthermore, we have deployed HiGR on a commercial platform under Tencent (serving hundreds of millions of users), and online A/B tests show that it increases average watch time and average video plays by 1.22\% and 1.73\%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24787
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HiGR: Efficient Generative Slate Recommendation via Hierarchical Planning and Multi-Objective Preference Alignment
Pang, Yunsheng
Liu, Zijian
Li, Yudong
Zhu, Shaojie
Luo, Zijian
Yu, Chenyun
Wu, Sikai
Shen, Shichen
Xu, Cong
Wang, Bin
Jiang, Kai
Yu, Hongyong
Zhuo, Chengxiang
Li, Zang
Information Retrieval
Artificial Intelligence
Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. Recent advances in generative models have shown significant potential for this task via autoregressive modeling of discrete semantic ID sequences. However, existing methods suffer from three key limitations: entangled item tokenization, inefficient sequential decoding, and the absence of holistic slate planning. These issues often result in substantial inference overhead and inadequate alignment with diverse user preferences and practical business requirements, hindering the industrial deployment of generative slate recommendation systems. In this paper, we propose HiGR, an efficient generative slate recommendation framework that integrates hierarchical planning with listwise preference alignment. First, we design an auto-encoder incorporating residual quantization and contrastive constraints, which tokenizes items into semantically structured IDs to enable controllable generation. Second, HiGR decouples the generation process into two stages: a list-level planning stage to capture global slate intent, and an item-level decoding stage to select specific items, effectively reducing the search space and enabling efficient generation. Third, we introduce a multi-objective and listwise preference alignment mechanism that enhances slate quality by leveraging implicit user feedback. Extensive experiments have validated the effectiveness of our HiGR method. Notably, it outperforms state-of-the-art baselines by over 10\% in offline recommendation quality while achieving a $5\times$ inference speedup. Furthermore, we have deployed HiGR on a commercial platform under Tencent (serving hundreds of millions of users), and online A/B tests show that it increases average watch time and average video plays by 1.22\% and 1.73\%, respectively.
title HiGR: Efficient Generative Slate Recommendation via Hierarchical Planning and Multi-Objective Preference Alignment
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2512.24787