LRGCL: LLM-refined graph contrastive learning for review-based recommendation

Abstract

Review-based recommendations commonly construct user-item interaction graphs in which textual review semantics serve as edge attributes. However, two practical limitations persist. First, raw reviews are inherently noisy: they often contain personal anecdotes, emotional expressions, and redundant phrasing that interfere with the preference-relevant signal on each edge. Second, many widely used graph contrastive learning methods generate positive views through random node or edge dropping, which may inadvertently discard semantically critical interactions and degrade the quality of learned representations. Although recent neighbor-aware methods have begun to address this limitation from structural or latent-semantic perspectives, review-based recommendation still lacks an edge-level semantic-preserving contrastive strategy that explicitly uses review evidence to protect key user-item interactions. To tackle these challenges, we propose LRGCL, an LLM-Refined Graph Contrastive Learning model for personalized recommendation. LRGCL first employs a large language model to refine each raw review into a concise, aspect-focused text that retains only key preference-feature information, and then encodes the refined review to obtain the edge semantic representation of the user-item bipartite graph. LRGCL further introduces a semantic-preserving contrastive objective in which key interaction edges are identified and preserved in augmented graph views, while only non-critical edges are dropped. Results across multiple datasets confirm that LRGCL achieves the lowest MSE and MAE among strong rating-based and review-based baselines, with especially clear MSE gains and smaller MAE margins on some domains. Ablation studies further verify the effectiveness of LLM-based review refinement and graph contrastive learning.