Recent advances in large language models (LLMs) offer new opportunities for recommender systems by capturing the nuanced semantics of user interests and item characteristics through rich semantic understanding and contextual reasoning. In particular, LLMs have been employed as rerankers that reorder candidate items based on inferred user-item relevance. However, these approaches often require expensive online inference-time reasoning, leading to high latency that hampers real-world deployment. In this work, we introduce Persona4Rec, a recommendation framework that performs offline reasoning to construct interpretable persona representations of items, enabling lightweight and scalable real-time inference. In the offline stage, Persona4Rec leverages LLMs to reason over item reviews, inferring diverse user motivations that explain why different types of users may engage with an item; these inferred motivations are materialized as persona representations, providing multiple, human-interpretable views of each item. Unlike conventional approaches that rely on a single item representation, Persona4Rec learns to align user profiles with the most plausible item-side persona through a dedicated encoder, effectively transforming user-item relevance into user-persona relevance. At the online stage, this persona-profiled item index allows fast relevance computation without invoking expensive LLM reasoning. Extensive experiments show that Persona4Rec achieves performance comparable to recent LLM-based rerankers while substantially reducing inference time. Moreover, qualitative analysis confirms that persona representations not only drive efficient scoring but also provide intuitive, review-grounded explanations. These results demonstrate that Persona4Rec offers a practical and interpretable solution for next-generation recommender systems.

翻译：大型语言模型（LLM）的最新进展为推荐系统带来了新的机遇，其通过丰富的语义理解和上下文推理能力，能够捕捉用户兴趣和物品特征的细微语义。特别是，LLM已被用作重排序器，根据推断的用户-物品相关性对候选物品进行重新排序。然而，这些方法通常需要昂贵的在线推理时间，导致高延迟，阻碍了实际部署。在本工作中，我们提出了Persona4Rec，一种通过离线推理构建可解释的物品角色表征的推荐框架，从而实现轻量级且可扩展的实时推理。在离线阶段，Persona4Rec利用LLM对物品评论进行推理，推断出解释不同类型用户可能与该物品互动的多样化用户动机；这些推断出的动机被具体化为角色表征，为每个物品提供多个可人为解释的视角。与依赖单一物品表征的传统方法不同，Persona4Rec通过一个专用编码器学习将用户画像与最可能的物品侧角色对齐，从而有效地将用户-物品相关性转化为用户-角色相关性。在在线阶段，这种基于角色画像的物品索引允许快速计算相关性，而无需调用昂贵的LLM推理。大量实验表明，Persona4Rec在显著减少推理时间的同时，取得了与近期基于LLM的重排序器相当的性能。此外，定性分析证实，角色表征不仅驱动高效的评分，还提供了直观的、基于评论的解释。这些结果表明，Persona4Rec为下一代推荐系统提供了一个实用且可解释的解决方案。