Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph

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.

Nowadays modern recommender systems on e-commerce websites are complicated and extremely sensitive to the response time, making calling LLM in real-time an unacceptable solution. So a natural idea is to distill useful knowledge from LLM into a knowledge graph (KG) and then apply the KG into recommendation for E-commerce. Trained on vast amounts of textual data and external knowledge sources, LLM is assumed to own world knowledge. So it is a relatively mild condition that LLM understands most use cases of products and user intention behind a product purchase. For instance, carnations are the official flower for mother’s day gift. However, it is extremely difficult to mine this kind of relation from data collected by e-commerce website. Customers typically don’t express their explicit intention (e.g., they buy carnations for their mothers) during their interactions with the website, which results in a fact that building product knowledge graph is very expensive and labor-intensive in e-commerce. We argue that LLM will narrow this gap significantly and enhance recommendation performance.