X-KGRank：一种基于知识图谱检索增强的推荐框架，通过模式挖掘与大语言模型重排序实现可解释推荐
X-KGRank: A Knowledge Graph RAG Framework for Explainable Recommendations via Pattern Mining and LLM Re-Ranking
浏览论文内容
中文总结 AI 辅助
X-KGRank是一种知识图谱检索增强推荐框架，结合协同过滤与LLM解释，在MovieLens-1M数据集上提升了推荐指标，且小参数LLM可实现相当的解释质量但更易产生事实错误。
中文摘要 AI 辅助
现代推荐系统生成的预测结果无法被用户质询，两种主流改进方向各有不足：协同过滤能捕捉行为信号但无法提供推理依据，而基于大语言模型（LLM）的推理虽能生成流畅解释，但存在幻觉问题且与用户历史的关联性较差。本文提出X-KGRank，一种将结构化协同过滤与LLM解释相统一的知识图谱检索增强框架。我们从MovieLens-1M数据集（包含6040名用户、3704个物品、988129条交互记录）构建了一个包含9762个节点、999264条边的异构知识图谱，涵盖RATED、HAS_GENRE、CO_RATED三种关系类型，存储于Neo4j中。我们训练了一个采用内容感知SBERT初始化、评分加权BPR目标的LightGCN排序器，并应用了流行度选择性路由策略：对长尾物品（3704个物品中的1855个）基于知识图谱路径进行锚定，对热门物品则利用预训练知识，使知识图谱增强生成的内容减少约50%。在MovieLens-1M测试集的99样本协议下，X-KGRank的NDCG@10为0.2956、Recall@10为0.5371，较强劲的流行度基线在这两个指标上提升17.1%；NDCG@20为0.3449，较基线（0.2983）提升15.6%；MRR为0.2435，较基线（0.2124）提升14.6%。在16个案例上评估的三种LLM主干中，15亿参数模型Qwen2.5-1.5B在启发式解释质量上与70亿参数模型Mistral-7B相当（分别为0.97和0.94），但定性分析显示较小模型更易出现事实编造问题。
英文摘要
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.
发表机构
- San Jose State University（圣何塞州立大学）
机构由 AI 辅助整理，请以论文原文为准。
