# REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing

arXiv: https://arxiv.org/abs/2510.01800 · HTML: https://mlsanity.com/paper/2510.01800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [A Survey on Text Classification: From Shallow to Deep Learning](https://mlsanity.com/paper/2008.00364/) (2020)
- [GRAG: Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2405.16506/) (2024)
- [Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2303.13948/) (2023)
- [RAG vs. GraphRAG: A Systematic Evaluation and Key Insights](https://mlsanity.com/paper/2502.11371/) (2025)
- [From Word Segmentation to POS Tagging for Vietnamese](https://mlsanity.com/paper/1711.04951/) (2017)
- [A Feature-Rich Vietnamese Named-Entity Recognition Model](https://mlsanity.com/paper/1803.04375/) (2018)

## Abstract (arXiv)

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.