Generative recommendation has recently emerged as a promising paradigm in information retrieval. However, generative ranking systems are still understudied, particularly with respect to their effectiveness and feasibility in large-scale industrial settings. This paper investigates this topic at the ranking stage of Xiaohongshu's Explore Feed, a recommender system that serves hundreds of millions of users. Specifically, we first examine how generative ranking outperforms current industrial recommenders. Through theoretical and empirical analyses, we find that the primary improvement in effectiveness stems from the generative architecture, rather than the training paradigm. To facilitate efficient deployment of generative ranking, we introduce GenRank, a novel generative architecture for ranking. We validate the effectiveness and efficiency of our solution through online A/B experiments. The results show that GenRank achieves significant improvements in user satisfaction with nearly equivalent computational resources compared to the existing production system.
View on arXiv@article{huang2025_2505.04180,
title={ Towards Large-scale Generative Ranking },
author={ Yanhua Huang and Yuqi Chen and Xiong Cao and Rui Yang and Mingliang Qi and Yinghao Zhu and Qingchang Han and Yaowei Liu and Zhaoyu Liu and Xuefeng Yao and Yuting Jia and Leilei Ma and Yinqi Zhang and Taoyu Zhu and Liujie Zhang and Lei Chen and Weihang Chen and Min Zhu and Ruiwen Xu and Lei Zhang },
journal={arXiv preprint arXiv:2505.04180},
year={ 2025 }
}