用知识图谱结构匹配解决复杂多约束问答难题
MC-RAG System: A Structure-Driven RAG System for Multi-Constraint Queries
- 将检索转为知识图谱上的子图匹配，实现结构化推理
- 支持医疗与百科类多约束查询，生成结果无事实错误
- 交互式可视化展示推理过程，适合需要可解释性的场景
检索增强生成（RAG）系统广泛应用于问答任务，但在处理复杂多约束查询时常出现约束违背、事实不一致或幻觉问题。本文提出面向多约束查询的结构驱动RAG系统（MC-RAG），将检索重构为知识图谱上的子图匹配问题。通过融合语义与结构嵌入，并结合路径级索引，MC-RAG实现了可解释、结构感知且约束一致的检索与生成。演示中用户可输入医学或百科类多约束查询，实时观察系统如何解析约束、执行结构匹配并生成答案，体验端到端、交互式且可解释的RAG流程。演示视频见 https://youtu.be/J8kahzmAnu0。
原文摘要 · Abstract (English)
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.
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。