Enriching Semantic Profiles into Knowledge Graph for Recommender Systems Using Large Language Models

2026-01-13

AI Summary

This work addresses the lack of a unified and effective framework for constructing semantically rich user preference profiles to enhance recommendation performance. We propose SPiKE, the first end-to-end profile-enhanced recommendation framework that systematically integrates the semantic compression capability of large language models (LLMs) with the structural propagation power of knowledge graphs (KGs). Specifically, SPiKE leverages LLMs to generate entity-level semantic profiles, injects them into the KG, and aligns LLM- and KG-derived representations during training to enable profile-aware graph aggregation and pairwise preference matching. Extensive experiments demonstrate that SPiKE significantly outperforms state-of-the-art methods that combine KGs and LLMs in real-world recommendation scenarios.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Preferences
• Machine Learning: Learning Preferences or Rankings

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Rich and informative profiling to capture user preferences is essential for improving recommendation quality. However, there is still no consensus on how best to construct and utilize such profiles. To address this, we revisit recent profiling-based approaches in recommender systems along four dimensions: 1) knowledge base, 2) preference indicator, 3) impact range, and 4) subject. We argue that large language models (LLMs) are effective at extracting compressed rationales from diverse knowledge sources, while knowledge graphs (KGs) are better suited for propagating these profiles to extend their reach. Building on this insight, we propose a new recommendation model, called SPiKE. SPiKE consists of three core components: i) Entity profile generation, which uses LLMs to generate semantic profiles for all KG entities; ii) Profile-aware KG aggregation, which integrates these profiles into the KG; and iii) Pairwise profile preference matching, which aligns LLM- and KG-based representations during training. In experiments, we demonstrate that SPiKE consistently outperforms state-of-the-art KG- and LLM-based recommenders in real-world settings.

Problem

• Semantic Profiles
• Knowledge Graph
• Recommender Systems
• Large Language Models
• User Preferences

Innovation

• Large Language Models
• Knowledge Graph
• Semantic Profile
• Recommender Systems
• Profile-aware Aggregation