用多维度信息构建用户与物品画像，实现可解释自适应推荐
MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation
- 从评论中无监督提取多方面信息生成结构化用户/物品画像
- 在多个数据集上推荐精度超越传统与基于LLM的基线方法
- 支持动态调整推理条件，适合需要透明推荐的场景
将大语言模型（LLMs）引入推荐系统的研究日益增多，但多数仍局限于简单的文本生成或静态提示推理，难以捕捉用户偏好与真实交互的复杂性。本文提出多维度驱动的LLM推荐代理MADRec，通过无监督方式从评论中提取多方面信息，构建用户与物品画像，并直接完成推荐、序列推荐与解释生成。MADRec采用基于方面-类别归纳的摘要方法生成结构化画像，并应用重排序机制构建高密度输入。当输出中缺失真实物品时，自反馈机制会动态调整推理标准。跨多个领域的实验表明，MADRec在精度和可解释性上均优于传统及基于LLM的基线方法，人工评估也证实其生成解释具有较强说服力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。