LLM-powered explanations: Unraveling recommendations through subgraph reasoning

Recommendation systems (RecSys) are pivotal in enhancing user experiences across various web applications by analyzing the complicated relationships between users and items. An explainable RecSys is crucial for the product development and subsequent decision-making. Knowledge graphs (KGs) have been widely used to enhance the performance of RecSys. However, KGs are known to be noisy and incomplete, making it hard to provide reliable explanations for recommendation results. We introduce a novel recommender that synergies Large Language Models (LLMs) and KGs to enhance the recommendation and provide interpretable results. We first harness the power of LLMs to augment KG reconstruction, where LLMs analyze and extract information from user reviews to generate new triples. In this way, we can enrich KGs with explainable paths that express user preferences. In addition, we introduce a novel subgraph reasoning module that effectively measures the importance of nodes and discovers reasoning for recommendation. Finally, these reasoning paths are fed into the LLMs to generate interpretable explanations of the recommendation results. Our approach significantly enhances both the effectiveness and interpretability of RecSys, especially in cross-selling scenarios where traditional methods falter. The effectiveness of our approach has been rigorously tested on four open real-world datasets, with our methods demonstrating a superior performance over contemporary state-of-the-art techniques by an average improvement of 12 %. The application of our model in a cross-selling RecSys for a multinational engineering and technology company further underscores its practical utility and potential to redefine recommendation practices through improved accuracy and user trust.