Integrating Heterogeneous Knowledge for Enhanced Recommendation with Large Language Models

The integration of Large Language Models into recommender systems has introduced a new paradigm in which models leverage their pre-trained knowledge to generate recommendations. A prevailing assumption is that an LLM’s inherent knowledge is sufficient to support high-quality recommendations across diverse domains. This paper challenges that assumption, positing that in specialized domains, recommendation efficacy is limited by the textual nature of an LLM’s knowledge. To address this limitation, we propose REKALM, a comprehensive integration framework for enhancing LLM-based recommenders through knowledge integration. Central to our approach is the extension of established text-conversion techniques to non-traditional data modalities. We utilize knowledge lexicalization , a process that translates heterogeneous data sources into a unified natural language format. This lexicalized corpus is then used in a knowledge-aware instruction-tuning pipeline to explicitly align the LLM’s internal representations with four distinct types of domain-specific information. We conduct experiments across four distinct domains to validate our framework. Our findings provide consistent empirical evidence that while an LLM’s inherent knowledge may suffice for universally familiar domains like movies, recommendation quality in more specialized areas is significantly improved through knowledge integration. The proposed approach demonstrates that augmenting LLMs with lexicalized, domain-specific knowledge is an effective system-level strategy for advancing the next generation of recommender systems.