Generative recommendation (GR) models generate items by autoregressively producing a sequence of discrete tokens that jointly index the target item. However, this autoregressive generation process also induces a structured decoding space whose impact on model expressiveness remains underexplored. Specifically, token-by-token generation can be viewed as traversing a decoding tree induced by semantic ID tokens, where leaf nodes correspond to candidate items. We observe that the item probabilities produced by GR models are strongly correlated with this tree structure: items that are close in the tree tend to receive similar probabilities for any given user, making it difficult to distinguish among them based on user-specific preferences. We further show theoretically that such structural correlations prevent GR models from representing even simple patterns that can be well captured by conventional collaborative filtering models. To mitigate this issue, we propose Latte, a simple modification that injects a latent token before each semantic ID, reshaping the decoding space from a single tree into multiple latent-token-conditioned trees. This design creates multiple paths with varying tree distances between items, relaxing tree-induced probability coupling and yielding an average of 3.45% relative improvement on NDCG@10. Our code is available at https://github.com/hyp1231/Latte.

翻译：生成式推荐（GR）模型通过自回归生成一系列离散标记（这些标记共同索引目标物品）来生成物品。然而，这种自回归生成过程也引入了结构化的解码空间，其对模型表达能力的影响尚待充分探究。具体而言，逐标记生成可视为遍历由语义ID标记诱导的解码树，其中叶节点对应候选物品。我们观察到，GR模型产生的物品概率与该树结构密切相关：在树中相近的物品对任意用户往往获得相似的概率，这使得基于用户特定偏好区分它们变得困难。我们进一步从理论上证明，此类结构相关性阻碍了GR模型表征甚至那些可由传统协同过滤模型有效捕获的简单模式。为缓解此问题，我们提出Latte——一种简单修改方案，在每个语义ID前注入隐式标记，从而将解码空间从单棵树重塑为多个隐式标记条件化的树。该设计在物品间创建了具有不同树距离的多条路径，松弛了树诱导的概率耦合，并在NDCG@10指标上平均带来3.45%的相对提升。我们的代码可在https://github.com/hyp1231/Latte获取。