This article explains why vector retrieval fails on multi‑hop reasoning, shows how Neo4j’s Cypher path traversal enables precise Graph RAG queries, outlines modeling best‑practices, demonstrates hybrid graph‑vector retrieval, compares Graph RAG with vector RAG, and lists common pitfalls to avoid.
This article explains why traditional vector RAG loses relational information, how GraphRAG reconstructs entity‑relationship triples into a knowledge graph, and provides step‑by‑step code, performance benchmarks, retrieval modes, and practical tips that raise multi‑hop reasoning accuracy from around 50% to 85%.
This article analyzes the Agentic‑R framework, which upgrades traditional single‑hop Retrieval‑Augmented Generation by introducing dual‑perspective scoring and a bidirectional flywheel, resulting in 2–3 absolute EM improvements across seven QA datasets and a 10–15% reduction in search rounds.
This talk presents recent advances in multi-step reasoning over large-scale, noisy knowledge graphs, introducing the Query2Box model that uses box embeddings for complex queries and the SMORE framework that enables efficient multi-hop inference on massive graphs through scalable query generation, embedding computation, and training pipelines.
The DataFun Summit 2022 Knowledge Graph Forum, held on March 12, presents cutting‑edge research on knowledge graph representation learning, multi‑hop reasoning, temporal KG question answering, and their applications in finance and retail, featuring talks by leading experts from JD, Fourth Paradigm, Stanford, and Meituan.
