用知识图谱+大模型实现可解释推荐，既准又可信。
X-KGRank: A Knowledge Graph RAG Framework for Explainable Recommendations via Pattern Mining and LLM Re-Ranking
- 构建异构知识图谱，结合协同过滤与大模型生成解释。
- 在MovieLens-1M上提升推荐准确率17.1%，召回率达53.7%
- 小模型也能生成高质量解释，适合资源有限场景
现代推荐系统缺乏可解释性。协同过滤捕捉用户行为但无推理能力，大语言模型（LLMs）虽能生成流畅解释却常幻觉且脱离用户历史。本文提出X-KGRank，一种基于知识图谱的检索增强框架，融合结构化协同过滤与大模型重排序。基于MovieLens-1M数据集（6,040用户，3,704物品，988,129次交互），构建包含9,762个节点、999,264条边的异构知识图谱，涵盖三种关系类型（RATED、HAS_GENRE、CO_RATED），存储于Neo4j。采用内容感知SBERT初始化的LightGCN排序器，结合评分加权BPR目标，并引入流行度选择路由策略，将长尾物品（1,855/3,704）通过知识图路径引导，热门物品直接调用预训练知识，使知识图谱增强生成减少约50%。在99样本测试协议下，X-KGRank在MovieLens-1M上达到NDCG@10 = 0.2956，Recall@10 = 0.5371，较强基线提升17.1%；在NDCG@20上达0.3449（+15.6%），MRR为0.2435（+14.6%）。在16个案例中评估三个LLM，15亿参数的Qwen2.5-1.5B在启发式解释质量上（0.97）接近70亿参数的Mistral-7B（0.94），但定性分析显示小模型更易编造事实。
原文摘要 · Abstract (English)
Modern recommender systems produce predictions that users cannot interrogate. The two dominant improvements, collaborative filtering and LLM-based reasoning, each fall short: collaborative filtering captures behavioural signals but offers no reasoning, while large language models (LLMs) generate fluent explanations but hallucinate and are poorly grounded in a user's history. We present X-KGRank, a knowledge graph retrieval augmented framework that unifies structural collaborative filtering with LLM-based explanation. From the MovieLens-1M dataset (6,040 users, 3,704 items, 988,129 interactions) we construct a heterogeneous knowledge graph of 9,762 nodes and 999,264 edges spanning three relation types (RATED, HAS_GENRE, and CO_RATED) persisted in Neo4j. We train a LightGCN ranker with content-aware SBERT initialization and a rating weighted BPR objective, and apply a popularity selective routing strategy that grounds long-tail items (1,855 of 3,704) in knowledge-graph paths while serving popular items from pre-trained knowledge, reducing KG-augmented generations by roughly 50%. On the MovieLens-1M test set under a 99-sample protocol, X-KGRank achieves NDCG@10 = 0.2956 and Recall@10 = 0.5371, improving over a strong popularity baseline by 17.1% on both metrics, by 15.6% on NDCG@20 (0.3449 vs. 0.2983), and by 14.6% on MRR (0.2435 vs. 0.2124). Across three LLM backbones evaluated on 16 cases, a 1.5-billion-parameter model (Qwen2.5-1.5B) matches a 7-billion-parameter model (Mistral-7B) on heuristic explanation quality (0.97 vs. 0.94), yet qualitative analysis shows the smaller model is more prone to factual fabrication.
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。