RAG Interview Questions, issue 24, Jul 28, 2026
The Resolution Limit Trap
Senior ML Engineer interview at Microsoft, and the interviewer asks:
“You built GraphRAG with Leiden for community detection. It’s deterministic, gives clean hierarchies, everyone’s happy. Now your retrieval quality is degrading on certain queries. When does maximizing modularity actively hurt you?”
Don’t say: “Leiden maximizes modularity to find well-connected communities, and it’s better than Louvain because it guarantees connected partitions.”
How Leiden community detection silently swallows your niche topics, and why optimizing for structural popularity is the fastest way to break semantic search.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.