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.

翻译：生成式推荐通过在紧凑的令牌空间中操作，已成为传统检索-排序流程的一种可扩展替代方案。然而，现有方法主要依赖于离散的代码级监督，这会导致信息损失，并限制了分词器与生成式推荐器之间的联合优化。在本工作中，我们提出了一种分布级监督范式，该范式利用多层码本上的概率分布作为信息丰富的软表示。基于这一思想，我们引入了语义导向分布对齐（SODA），这是一个基于贝叶斯个性化排序的即插即用对比监督框架。该框架通过负KL散度对齐语义丰富的分布，同时支持端到端的可微分训练。在多个真实世界数据集上的大量实验表明，SODA能够持续提升各种生成式推荐器骨干模型的性能，验证了其有效性和通用性。代码将在论文被接受后公开。