Boosting Knowledge Graph-based Recommendations through Confidence-Aware Augmentation with Large Language Models

2025-02-06

AI Summary

To address critical challenges in knowledge graph (KG)-based recommendation—including high graph noise, difficulty in KG updating, and hallucination interference from large language models (LLMs)—this paper proposes a trust-enhanced KG-LLM collaborative recommendation framework. Methodologically, it introduces a novel confidence-aware subgraph enhancement mechanism, integrating confidence-guided message passing with dual-view contrastive learning, and incorporates an explainability generation module. Technically, the framework synergizes LLM-based semantic understanding, confidence modeling, graph neural networks, and contrastive learning to achieve dynamic KG denoising and semantic alignment. Extensive experiments on multiple public benchmarks demonstrate significant improvements in both recommendation accuracy and explainability, while effectively mitigating KG noise and LLM hallucinations. This work establishes a new paradigm for trustworthy, KG-augmented recommendation systems.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

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

Abstract

Knowledge Graph-based recommendations have gained significant attention due to their ability to leverage rich semantic relationships. However, constructing and maintaining Knowledge Graphs (KGs) is resource-intensive, and the accuracy of KGs can suffer from noisy, outdated, or irrelevant triplets. Recent advancements in Large Language Models (LLMs) offer a promising way to improve the quality and relevance of KGs for recommendation tasks. Despite this, integrating LLMs into KG-based systems presents challenges, such as efficiently augmenting KGs, addressing hallucinations, and developing effective joint learning methods. In this paper, we propose the Confidence-aware KG-based Recommendation Framework with LLM Augmentation (CKG-LLMA), a novel framework that combines KGs and LLMs for recommendation task. The framework includes: (1) an LLM-based subgraph augmenter for enriching KGs with high-quality information, (2) a confidence-aware message propagation mechanism to filter noisy triplets, and (3) a dual-view contrastive learning method to integrate user-item interactions and KG data. Additionally, we employ a confidence-aware explanation generation process to guide LLMs in producing realistic explanations for recommendations. Finally, extensive experiments demonstrate the effectiveness of CKG-LLMA across multiple public datasets.

Problem

• Enhancing Knowledge Graph accuracy
• Integrating Large Language Models efficiently
• Improving recommendation quality with confidence-awareness

Innovation

• LLM-based subgraph augmentation
• Confidence-aware message propagation
• Dual-view contrastive learning method