Recommender systems play a vital role in various online services. However, the insulated nature of training and deploying separately within a specific domain limits their access to open-world knowledge. Recently, the emergence of large language models (LLMs) has shown promise in bridging this gap by encoding extensive world knowledge and demonstrating reasoning capability. Nevertheless, previous attempts to directly use LLMs as recommenders have not achieved satisfactory results. In this work, we propose an Open-World Knowledge Augmented Recommendation Framework with Large Language Models, dubbed KAR, to acquire two types of external knowledge from LLMs -- the reasoning knowledge on user preferences and the factual knowledge on items. We introduce factorization prompting to elicit accurate reasoning on user preferences. The generated reasoning and factual knowledge are effectively transformed and condensed into augmented vectors by a hybrid-expert adaptor in order to be compatible with the recommendation task. The obtained vectors can then be directly used to enhance the performance of any recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from the LLM. Extensive experiments show that KAR significantly outperforms the state-of-the-art baselines and is compatible with a wide range of recommendation algorithms.

翻译：推荐系统在各种在线服务中扮演着重要角色。然而，其训练和部署在特定领域内独立进行的内生特性限制了其对开放世界知识的获取。近期，大语言模型的出现通过编码广泛的世界知识并展现推理能力，为弥合这一差距带来了前景。尽管如此，此前直接使用大语言模型作为推荐系统的尝试并未取得令人满意的结果。本文提出一种基于大语言模型的开放世界知识增强推荐框架，即KAR，以从大语言模型中获取两类外部知识——关于用户偏好的推理知识和关于物品的事实知识。我们引入因子化提示方法，以引发对用户偏好的精确推理。通过混合专家适配器，生成的推理知识和事实知识被有效转换并压缩为增强向量，从而与推荐任务兼容。所得向量可直接用于提升任意推荐模型的性能。此外，我们通过预处理和预存储大语言模型中的知识来确保高效推理。大量实验表明，KAR显著优于当前最先进的基线方法，并能与多种推荐算法兼容。