Generative recommendation has emerged as a scalable alternative to traditional retrieve-and-rank pipelines by operating in a compact token space. However, existing methods mainly rely on discrete code-level supervision, which leads to information loss and limits the joint optimization between the tokenizer and the generative recommender. In this work, we propose a distribution-level supervision paradigm that leverages probability distributions over multi-layer codebooks as soft and information-rich representations. Building on this idea, we introduce Semantic-Oriented Distributional Alignment (SODA), a plug-and-play contrastive supervision framework based on Bayesian Personalized Ranking, which aligns semantically rich distributions via negative KL divergence while enabling end-to-end differentiable training. Extensive experiments on multiple real-world datasets demonstrate that SODA consistently improves the performance of various generative recommender backbones, validating its effectiveness and generality. Codes will be available upon acceptance.
@article{arxiv.2603.00700,
title = {SODA: Semantic-Oriented Distributional Alignment for Generative Recommendation},
author = {Ziqi Xue and Dingxian Wang and Yimeng Bai and Shuai Zhu and Jialei Li and Xiaoyan Zhao and Frank Yang and Andrew Rabinovich and Yang Zhang and Pablo N. Mendes},
journal= {arXiv preprint arXiv:2603.00700},
year = {2026}
}