Language Models (LMs) have been widely used in recommender systems to incorporate textual information of items into item IDs, leveraging their advanced language understanding and generation capabilities. Recently, generative recommender systems have utilized the reasoning abilities of LMs to directly generate index tokens for potential items of interest based on the user's interaction history. To inject diverse item knowledge into LMs, prompt templates with detailed task descriptions and various indexing techniques derived from diverse item information have been explored. This paper focuses on the inconsistency in outputs generated by variations in input prompt templates and item index types, even with the same user's interaction history. Our in-depth quantitative analysis reveals that preference knowledge learned from diverse prompt templates and heterogeneous indices differs significantly, indicating a high potential for complementarity. To fully exploit this complementarity and provide consistent performance under varying prompts and item indices, we propose MVIGER, a unified variational framework that models selection among these information sources as a categorical latent variable with a learnable prior. During inference, this prior enables the model to adaptively select the most relevant source or aggregate predictions across multiple sources, thereby ensuring high-quality recommendation across diverse template-index combinations. We validate the effectiveness of MVIGER on three real-world datasets, demonstrating its superior performance over existing generative recommender baselines through the effective integration of complementary knowledge.

翻译：语言模型（LMs）凭借其先进的语言理解与生成能力，已被广泛应用于推荐系统，将物品的文本信息融入物品标识符中。近期，生成式推荐系统利用LMs的推理能力，直接根据用户交互历史生成潜在兴趣物品的索引标记。为向LMs注入多样化的物品知识，研究者探索了包含详细任务描述的提示模板，以及从多元物品信息衍生的各类索引技术。本文聚焦于以下现象：即使基于相同的用户交互历史，输入提示模板的差异与物品索引类型的变化也会导致输出结果不一致。我们深入的定量分析表明，从不同提示模板和异构索引中学得的偏好知识存在显著差异，显示出高度的互补潜力。为充分利用这种互补性，并在变化提示与物品索引下提供稳定性能，我们提出MVIGER——一个统一的变分框架，该框架将信息源选择建模为具有可学习先验的类别隐变量。在推理过程中，此先验使模型能自适应选择最相关的信息源或聚合多源预测，从而确保在不同模板-索引组合下均能实现高质量推荐。我们在三个真实数据集上验证了MVIGER的有效性，结果表明其通过有效融合互补知识，性能显著优于现有生成式推荐基线方法。