A core objective in recommender systems is to accurately model the distribution of user preferences over items to enable personalized recommendations. Recently, driven by the strong generative capabilities of large language models (LLMs), LLM-based generative recommendation has become increasingly popular. However, we observe that existing methods inevitably introduce systematic bias when estimating item-level preference distributions. Specifically, autoregressive generation suffers from incomplete coverage due to beam search pruning, while parallel generation distorts probabilities by assuming token independence. We attribute this issue to a fundamental modeling mismatch: these methods approximate item-level distributions via token-level generation, which inherently induces approximation errors. Through both theoretical analysis and empirical validation, we demonstrate that token-level generation cannot faithfully substitute item-level generation, leading to biased item distributions. To address this, we propose \textbf{Sim}ply \textbf{G}enerative \textbf{R}ecommendation (\textbf{SimGR}), a framework that directly models item-level preference distributions in a shared latent space and ranks items by similarity, thereby aligning the modeling objective with recommendation and mitigating distributional distortion. Extensive experiments across multiple datasets and LLM backbones show that SimGR consistently outperforms existing generative recommenders. Our code is available at https://anonymous.4open.science/r/SimGR-C408/

翻译：推荐系统的一个核心目标是准确建模用户对物品偏好的分布，以实现个性化推荐。近年来，在大语言模型（LLMs）强大生成能力的推动下，基于LLM的生成式推荐日益流行。然而，我们观察到现有方法在估计物品级偏好分布时不可避免地引入了系统性偏差。具体而言，自回归生成因束搜索剪枝而存在覆盖不全的问题，而并行生成则通过假设标记独立性而扭曲了概率。我们将此问题归因于一个根本的建模失配：这些方法通过标记级生成来近似物品级分布，这本质上引入了近似误差。通过理论分析和实证验证，我们证明标记级生成无法忠实地替代物品级生成，从而导致有偏的物品分布。为解决此问题，我们提出了\textbf{Sim}ply \textbf{G}enerative \textbf{R}ecommendation（\textbf{SimGR}），这是一个直接在共享潜在空间中建模物品级偏好分布并通过相似性对物品进行排序的框架，从而使建模目标与推荐任务对齐，并减轻分布失真。在多个数据集和LLM骨干网络上进行的广泛实验表明，SimGR始终优于现有的生成式推荐方法。我们的代码可在 https://anonymous.4open.science/r/SimGR-C408/ 获取。