MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation
This addresses the need for more adaptive and explainable recommender systems for users, though it appears incremental by building on existing LLM integration efforts.
The study tackled the problem of integrating large language models into recommender systems by proposing MADRec, an autonomous LLM agent that constructs multi-aspect user and item profiles from reviews for recommendations and explanations, resulting in outperformance over baselines in precision and explainability as confirmed by experiments and human evaluation.
Recent attempts to integrate large language models (LLMs) into recommender systems have gained momentum, but most remain limited to simple text generation or static prompt-based inference, failing to capture the complexity of user preferences and real-world interactions. This study proposes the Multi-Aspect Driven LLM Agent MADRec, an autonomous LLM-based recommender that constructs user and item profiles by unsupervised extraction of multi-aspect information from reviews and performs direct recommendation, sequential recommendation, and explanation generation. MADRec generates structured profiles via aspect-category-based summarization and applies Re-Ranking to construct high-density inputs. When the ground-truth item is missing from the output, the Self-Feedback mechanism dynamically adjusts the inference criteria. Experiments across multiple domains show that MADRec outperforms traditional and LLM-based baselines in both precision and explainability, with human evaluation further confirming the persuasiveness of the generated explanations.