MC-RAG System: A Structure-Driven RAG System for Multi-Constraint Queries
2026-07-11 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors created a new question-answering system called MC-RAG that is better at handling tricky questions with multiple requirements. Instead of just looking up information, it matches parts of questions to a knowledge graph, which is like a web of facts connected by their relationships. This approach helps the system give answers that follow all the constraints and avoid mistakes. They also provide a demo where users can see how the system works step-by-step.
Retrieval-Augmented Generationknowledge graphsubgraph matchingsemantic embeddingsstructural embeddingsmulti-constraint queriesconstraint satisfactionpath-level indexingfactual consistencyquestion answering
Authors
Xiao Zhang, Yang Wan, Yi Li, Miao Xie, Chunli Lv
Abstract
Retrieval-Augmented Generation (RAG) systems are widely adopted in question answering, yet they often fail to satisfy complex multi-constraint queries, leading to constraint violations, factual inconsistencies, or hallucinations. We present Structure-Driven RAG System for Multi-Constraint Queries(MC-RAG), a structure-driven RAG system that reformulates retrieval as a subgraph matching problem over a knowledge graph. By integrating semantic and structural embeddings with path-level indexing, MC-RAG performs interpretable, structure-aware, and constraint-consistent retrieval and generation. During the demonstration, participants can input medical or encyclopedic multi-constraint queries, visualize how the system parses constraints, performs structural matching, and generates answers, thereby experiencing an end-to-end, interactive, and explainable RAG pipeline. A demo video is available at https://youtu.be/J8kahzmAnu0.