NGM-RAG: Neural Graph Matching Improves Retrieval-Augmented Generation for Complex Reasoning

Jul 14, 2026

A new framework, NGM-RAG, integrates graph construction, graph matching, and answer generation to enhance retrieval-augmented generation (RAG) for large language models. By combining text-based and graph-based retrieval using neural graph matching and adaptive weighting, NGM-RAG better captures relational knowledge. Experiments show that NGM-RAG outperforms NaiveRAG, GraphRAG, and LightRAG on multi-hop question answering and long-context summarization tasks.

Why it matters: This approach addresses a key limitation of traditional RAG by enabling more effective multi-hop reasoning, potentially improving LLM performance on complex information-seeking tasks.

Full story at: arXiv Information Retrieval ↗