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.
From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system
Department of Technological Innovation Management, Faculty of Engineering, University of Mons (UMONS), Mons, Belgium（蒙斯大学工程学院技术创新管理系）；Department of Mathematics and Operational Research, Faculty of Engineering, University of Mons (UMONS), Mons, Belgium（蒙斯大学工程学院数学与运筹学系）；Department of Mathematics（数学系）；Operational Research, Faculty of Engineering, University of Mons (UMONS), Mons, Belgium（运筹学系）
University of Cambridge（剑桥大学）；UC Berkeley（加州大学伯克利分校）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
两阶段推荐系统由于其可扩展性和可维护性而被工业界广泛采用。这些系统通过两个步骤产生推荐：（i）多个提名者使用便宜的计算项目嵌入从大池中预选少量项目;（ii）具有更丰富的功能集，排名器重新排列提名项目并将其提供给用户。这种设置的一个关键挑战是，孤立的每个阶段的最佳性能并不意味着最佳的全局性能。针对这一问题，Ma et al.（2020）提出了一种由排名者推荐每个项目的概率加权的提名者训练目标重要性。在这项工作中，我们专注于探索的补充问题。建模为一个上下文的强盗问题，我们发现LinUCB（一个接近最佳的探索策略，单阶段系统）可能会导致线性遗憾时，部署在两阶段的搜索器。因此，我们提出了一种方法，同步之间的排名和提名的探索策略。我们的算法只依赖于标准LinUCB在每个阶段已经计算的数量，并且可以在三行额外的代码中实现。最后，我们通过实验证明了我们的算法的有效性。
Rethinking Semantic Collaborative Integration: Why Alignment Is Not Enough
City University of Hong Kong（香港城市大学）；Hong Kong Institute of AI for Science（香港人工智能科学研究所）；Beihang University（北京航空航天大学）；Chinese University of Hong Kong（香港中文大学）；Jingdong（京东）
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph
Tsinghua University（清华大学）；University of Southern California（南加利福尼亚大学）
可解释性和有效性是构建推荐系统的两个关键方面。以前的努力主要集中在合并边信息，以实现更好的推荐性能。然而，这些方法具有一些弱点：（1）基于神经网络的嵌入方法的预测难以解释和调试;（2）基于符号、图形的方法（例如，基于Meta路径的模型）需要人工努力和领域知识来定义模式和规则，并且忽略项目关联类型（例如，可替换的和互补的）。在本文中，我们提出了一种新的联合学习框架集成\textit{induction of explainable rules from knowledge graph}与\textit{construction of a rule-guided neural recommendation model}。该框架鼓励两个模块相互补充，以产生有效的和可解释的推荐：1）归纳规则，从以项目为中心的知识图谱中挖掘，总结常见的多跳关系模式，用于推断不同的项目关联，并为模型预测提供人类可读的解释; 2）推荐模块可以通过归纳规则进行扩充，从而在处理冷启动问题时具有更好的泛化能力。大量的实验\footnote{Code and data can be found at: \url{https://github.com/THUIR/RuleRec}}表明，我们提出的方法已经取得了显着的改善，在现实世界的数据集上的基线项目推荐。我们的模型在通过将项目名称链接到相关实体而生成的“嘈杂”项目知识…
MMHCL: Multi-Modal Hypergraph Contrastive Learning for Recommendation
School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）；Shituoyun (Nanjing) Technology Co., Ltd（石墨云（南京）科技有限公司）；School of Artificial Intelligence, Beijing Normal University（人工智能学院，北京师范大学）
OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Shopee Pte. Ltd.（虾皮有限公司）；Nanyang Technological University（南洋理工大学）
