August 12, 2026· ~7 min readNL2GQL and Text2Cypher in 2026: The New NL2SQL # NL2GQL and Text2Cypher in 2026: The New NL2SQL Natural language → SQL (NL2SQL) has been a research staple for a decade. In 2026, the graph world i
July 30, 2026· ~6 min readCrystallis: Coordinated Multi-View Visualisation Generation with Large Language Models > **Teaser:** LLMs can generate individual charts, but multi-view dashboards require colour consistency, shared scales, and narrative coherence acros
July 15, 2026· ~4 min readWhen to Use Graphs in RAG: Findings from the ICLR 2026 GraphRAG-Bench Study # When to Use Graphs in RAG Despite GraphRAG's conceptual promise, recent studies have shown that it frequently underperforms vanilla vector RAG on
July 11, 2026· ~11 min readKnowledge Graph Construction from Unstructured Data: Building the Pipeline ## Why Construction Is the Hard Part Knowledge graphs are only as valuable as the data they contain. Querying, visualising, and reasoning over a gra
June 8, 2026· ~8 min readGraphRAG Reality Check: When It Fails, Why, and How to Fix It # GraphRAG Reality Check: When It Fails, Why, and How to Fix It GraphRAG is oversold. Marketing promises structured knowledge retrieval that "connec
June 8, 2026· ~11 min readGraphRAG for $30: Lazy Extraction That Actually Works ## Introduction The dirty secret of early GraphRAG deployments in 2024: indexing a million-document corpus cost $30,000+ in LLM API tokens. Before a