REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing
This work addresses the problem of interpreting and complying with institutional policies for students, representing an incremental improvement in domain-specific advisory systems.
The paper tackles the challenge of building effective academic regulation advising systems by proposing REBot, an LLM-enhanced chatbot using CatRAG, a hybrid retrieval-reasoning framework, which achieves state-of-the-art performance with an F1 score of 98.89% on regulation-specific tasks.
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.