Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph
This work addresses the need for explainable recommendations in e-commerce, offering a practical solution for businesses, though it is incremental as it builds on existing LLM and knowledge graph methods.
The paper tackled the problem of leveraging large language models for e-commerce recommendation by proposing LLM-PKG, which distills LLM knowledge into a product knowledge graph to provide explainable recommendations, resulting in significant improvements in user engagements and transactions as shown in an A/B test.
How to leverage large language model's superior capability in e-commerce recommendation has been a hot topic. In this paper, we propose LLM-PKG, an efficient approach that distills the knowledge of LLMs into product knowledge graph (PKG) and then applies PKG to provide explainable recommendations. Specifically, we first build PKG by feeding curated prompts to LLM, and then map LLM response to real enterprise products. To mitigate the risks associated with LLM hallucination, we employ rigorous evaluation and pruning methods to ensure the reliability and availability of the KG. Through an A/B test conducted on an e-commerce website, we demonstrate the effectiveness of LLM-PKG in driving user engagements and transactions significantly.