Unleashing the Power of Large Language Model for Denoising Recommendation

2025-02-13

AI Summary

Noise in implicit feedback data severely degrades recommender system performance, while existing denoising methods suffer from reliance on low-quality auxiliary information, extreme data sparsity, and strong prior assumptions. To address these limitations, we propose LLaRD—a novel framework that for the first time integrates Chain-of-Thought (CoT) reasoning into user-item interaction graph inference to explicitly model denoising relationships. Furthermore, guided by the Information Bottleneck (IB) principle, LLaRD constrains the semantic knowledge generated by large language models (LLMs) to align tightly with the recommendation objective, enabling controllable semantic enhancement. Crucially, LLaRD requires no additional annotations or domain-specific assumptions. Extensive experiments on multiple benchmark datasets demonstrate substantial improvements in both denoising accuracy and recommendation performance, consistently outperforming state-of-the-art methods.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Recommender Systems
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recommender systems are crucial for personalizing user experiences but often depend on implicit feedback data, which can be noisy and misleading. Existing denoising studies involve incorporating auxiliary information or learning strategies from interaction data. However, they struggle with the inherent limitations of external knowledge and interaction data, as well as the non-universality of certain predefined assumptions, hindering accurate noise identification. Recently, large language models (LLMs) have gained attention for their extensive world knowledge and reasoning abilities, yet their potential in enhancing denoising in recommendations remains underexplored. In this paper, we introduce LLaRD, a framework leveraging LLMs to improve denoising in recommender systems, thereby boosting overall recommendation performance. Specifically, LLaRD generates denoising-related knowledge by first enriching semantic insights from observational data via LLMs and inferring user-item preference knowledge. It then employs a novel Chain-of-Thought (CoT) technique over user-item interaction graphs to reveal relation knowledge for denoising. Finally, it applies the Information Bottleneck (IB) principle to align LLM-generated denoising knowledge with recommendation targets, filtering out noise and irrelevant LLM knowledge. Empirical results demonstrate LLaRD's effectiveness in enhancing denoising and recommendation accuracy.

Problem

• Enhance denoising in recommender systems
• Leverage large language models for noise reduction
• Improve recommendation accuracy using semantic insights

Innovation

• LLM for denoising
• Chain-of-Thought technique
• Information Bottleneck principle