Common Sense Enhanced Knowledge-based Recommendation with Large Language Model

Shenghao Yang, Weizhi Ma, Peijie Sun, Min Zhang, Qingyao Ai, Yiqun Liu, Mingchen Cai

Abstract: Knowledge-based recommendation models effectively alleviate the data sparsity issue leveraging the side information in the knowledge graph, and have achieved considerable performance. Nevertheless, the knowledge graphs used in previous work, namely metadata-based knowledge graphs, are usually constructed based on the item attributes and co-occurring relations (e.g., also buy), in which the former provides limited information and the latter relies on sufficient interaction data and still suffers from data sparsity issue. Common sense, as a knowledge form with generality and universality, can be used as a supplement to the metadata-based knowledge graph and provides a new perspective for modeling users’ preferences. Recently, benefiting from the emergent knowledge of the Large Language Model, efficient acquisition of common sense has become possible. This paper proposes a novel knowledge-based recommendation framework incorporating common sense, namely CSRec, which can be flexibly coupled with existing knowledge-based methods. Considering the challenge of the knowledge gap between the common sense- and metadata-based knowledge graph, we propose a knowledge fusion approach based on mutual information maximization theory. Experimental results on public datasets demonstrate that our approach significantly improves the performance of existing knowledge-based recommendation models.