用知识图谱增强的检索推理框架，提升学术政策问答准确率
REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing
- 构建分层带标签的知识图谱，融合语义特征与密集检索
- 在特定数据集上实现98.89%的F1分数，优于现有方法
- 适合教育咨询系统开发人员和政策类AI应用研究者
学术规范咨询对帮助学生理解并遵守校规至关重要，但构建有效系统需依赖领域特定的法规资源。为此，我们提出REBot，一个基于CatRAG（一种结合检索增强生成与图推理的混合检索推理框架）的大型语言模型增强型咨询聊天机器人。CatRAG统一了密集检索与图推理，依托一个分层、类别标注的知识图谱，并通过语义特征增强实现领域对齐。轻量级意图分类器将查询路由至合适的检索模块，确保事实准确性与上下文深度。我们构建了一个专用于法规的语料库，并在分类与问答任务上评估REBot，取得98.89%的F1分数，达到当前最优水平。最后，我们实现了一个网页应用，展示了REBot在真实学术咨询场景中的实用价值。
原文摘要 · Abstract (English)
Academic regulation advising is essential for helping students interpret and comply with institutional policies, yet building effective systems requires domain specific regulatory resources. To address this challenge, we propose REBot, an LLM enhanced advisory chatbot powered by CatRAG, a hybrid retrieval reasoning framework that integrates retrieval augmented generation with graph based reasoning. CatRAG unifies dense retrieval and graph reasoning, supported by a hierarchical, category labeled knowledge graph enriched with semantic features for domain alignment. A lightweight intent classifier routes queries to the appropriate retrieval modules, ensuring both factual accuracy and contextual depth. We construct a regulation specific dataset and evaluate REBot on classification and question answering tasks, achieving state of the art performance with an F1 score of 98.89%. Finally, we implement a web application that demonstrates the practical value of REBot in real world academic advising scenarios.
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。